CN112734457A - Hotel guest room dynamic pricing method, device, equipment and storage medium - Google Patents

Hotel guest room dynamic pricing method, device, equipment and storage medium Download PDF

Info

Publication number
CN112734457A
CN112734457A CN202011565991.XA CN202011565991A CN112734457A CN 112734457 A CN112734457 A CN 112734457A CN 202011565991 A CN202011565991 A CN 202011565991A CN 112734457 A CN112734457 A CN 112734457A
Authority
CN
China
Prior art keywords
hotel
price
room
dynamic
demand
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011565991.XA
Other languages
Chinese (zh)
Inventor
李盛
王浩
柴圣琪
韩轶
李越
郝峻晟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Yungoal Information Technology Co ltd
Original Assignee
Shanghai Yungoal Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Yungoal Information Technology Co ltd filed Critical Shanghai Yungoal Information Technology Co ltd
Priority to CN202011565991.XA priority Critical patent/CN112734457A/en
Publication of CN112734457A publication Critical patent/CN112734457A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0206—Price or cost determination based on market factors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/12—Hotels or restaurants

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Game Theory and Decision Science (AREA)

Abstract

The invention discloses a hotel room dynamic pricing method, a device, equipment and a storage medium, which utilize historical data of a hotel and combine the actual situation of the hotel to dynamically set the daily sales price of the hotel room in a pre-sale period and improve the income of the hotel. And for historical data, the truncated data is restored and the periodic and seasonal factors are stripped off due to the limitation of the total number of the guest rooms, so that demand data only depending on prices is obtained and is used for predicting the prices of the remaining guest rooms. And obtaining the optimal dynamic price of the hotel in the pre-sale period by solving the dynamic game model. The invention can be used for helping hotel management personnel to dynamically adjust the sale price of hotel rooms in the pre-sale period, and solves the problems of low income and insufficient competitiveness caused by pricing the rooms according to the experience of the hotel management personnel in the traditional hotel industry.

Description

Hotel guest room dynamic pricing method, device, equipment and storage medium
Technical Field
The invention belongs to the technical field of hotel income management, and particularly relates to a hotel guest room dynamic pricing method, device, equipment and storage medium.
Background
The daily gain of a hotel depends on the number of rooms sold, and the price of each sold room. The hotel can be through setting up the polymorphic type guest room of different price levels to and different room price rules and products, thereby subdivide different sources of guests, obtain higher income finally. Then, how to maximize the income of the hotel, the income management is an important indispensable link.
The profit Management (RM) is a dynamic Management process that continuously optimizes products, prices and sales channels, improves product sales volume and sales price, and realizes profit maximization by analyzing and predicting market supply-demand relationship and consumer purchasing habits.
In the case of the hotel industry, revenue management can be understood as a strategy for maximizing the revenue of a hotel by selling a suitable product to a suitable guest at a suitable price through a suitable channel at a suitable time by the hotel.
The price of the guest room reflects the income condition of the hotel most directly, and the income and the profitability of the hotel can be further improved by adjusting the price of the guest room of the hotel, so that the maximization of the total income is realized.
However, the traditional hotel pricing is often based on experience to make decisions, which is generally limited by the work experience and the reading of a pricing person, and the traditional hotel pricing has strong subjectivity and cannot effectively improve the total income.
Disclosure of Invention
The invention aims to provide a hotel room dynamic pricing method, a device, equipment and a storage medium, which are used for pricing hotel rooms based on a demand function and a dynamic game and solve the problems of low income and insufficient competitiveness caused by pricing the hotel rooms according to experience in the traditional hotel industry.
In order to solve the problems, the technical scheme of the invention is as follows:
a hotel room dynamic pricing method comprises the following steps:
collecting historical data of each room type of the hotel, and processing the historical data to obtain historical data of the price demand of the rooms;
fitting a price demand function based on the historical data of the guest room price demand to predict the demands corresponding to different price points;
establishing a dynamic game model of hotel room pricing and customer requirements based on a dynamic game theory;
setting the highest price and the lowest price of a hotel room, and obtaining the probability distribution of the order accepted by the customer according to the ratio of the highest price and the lowest price accepted by the customer;
and optimizing the profit model according to the probability distribution of the order received by the customer, the number of required guestrooms and the balanced solution of the dynamic game model, and solving to obtain the dynamic price of the hotel guestrooms in the pre-sale period.
According to an embodiment of the present invention, the step S1 further includes:
s11: for historical data, due to the limitation of the total number of the guest rooms, the maximum preset number of the guest rooms is the total number of the guest rooms, but the real demand of customers can be larger than the total number of the guest rooms, when the preset number of the guest rooms is the maximum, the corresponding demand of the customers can be cut off, a limited dependent variable regression method is used for processing the problem of right cutting of the demand caused by the limitation of the number of the guest rooms, the historical data are restored to the state without cutting off, and the periodic and seasonal factors are stripped;
s12: solving main periodic and seasonal factor factors including a week factor, a ten-day factor and a month factor;
wherein, the calculation formula of each factor is as follows:
week factor:
Figure BDA0002860936970000021
factor of ten days:
Figure BDA0002860936970000022
monthly factor:
Figure BDA0002860936970000023
the formula of the demand after stripping off the seasonal factors is as follows:
Figure BDA0002860936970000024
wherein the content of the first and second substances,
Figure BDA0002860936970000025
and
Figure BDA0002860936970000026
respectively the average requirements of each week, each ten-day and each month in the historical data;
Figure BDA0002860936970000027
is the overall average demand;
Figure BDA0002860936970000028
to cut off the demand after reduction.
Wti、EtjAnd MtkAll values are between 0 and 1 and satisfy
Figure BDA0002860936970000031
And
Figure BDA0002860936970000032
if the day of residence t is on day i of the week, then Wti1 is ═ 1; otherwise, Wti0; if the ten-day degree of the entering date t is j, Etj1 is ═ 1; otherwise, Etj0; if the month of the entering-living day t is k, Mtk1 is ═ 1; otherwise, Mtk＝0。
According to an embodiment of the present invention, the step S11 further includes: and (3) adopting a Tobit regression or multiple logistic regression model to process the problem of right truncation of the demand caused by the limitation of the number of guest rooms and restore the historical data into a non-truncated state.
According to an embodiment of the present invention, the step S2 further includes:
based on the historical data of the guest room price demand, a local slope updating algorithm or a least square method is adopted to fit a price demand function.
According to an embodiment of the present invention, the step S3 further includes:
in the dynamic game model, the game of the hotel and the customer about the guest room pricing is a non-antagonistic cooperative game, the hotel and the customer conspire to jointly obtain as much benefit as possible, and the ideal outcome pursued by the hotel is that the benefit of the hotel is as much as possible on the basis of the reservation of the customer; in the process of establishing the dynamic game model, a hotel firstly makes a pre-sale price of a guest room, and then generates two different prediction benefits according to a feedback result of reservation or non-reservation of a customer; according to the income prediction result, the decision of the hotel is to adjust the pre-sale price of the guest room on the premise of customer reservation.
According to an embodiment of the present invention, the step S4 further includes:
s41: the maximum price f of the guest room is set according to the actual condition of the hotelmax；
S42: according to the fitted price demand function in the step S2, taking the price corresponding to the actual remaining stock of the guest room on the stay day as the minimum price fmin；
S43: calculating the maximum acceptable guest room price f through historical datamaxThe customer ratio of (a) is θ;
Figure BDA0002860936970000033
s44 the probability distribution from the guest room to the customer accepting the guest room price to order is:
Figure BDA0002860936970000034
according to an embodiment of the present invention, the step S5 further includes:
s51: fitting the Poisson distribution of the number of the required guest rooms in the pre-sale period according to the annual data of the number of the required guest rooms in the historical data:
Figure BDA0002860936970000041
wherein the intensity lambdatThe number of the required guest rooms on the t day;
s52: the revenue function of each guest room in the pre-sale period of the hotel is as follows:
Figure BDA0002860936970000042
wherein
Figure BDA0002860936970000043
The optimal price of the current day of guest rooms of the hotel in the pre-sale period is set;
s53: the expected revenue of each day of the guest room during the pre-sale period of the hotel is:
Figure BDA0002860936970000044
s54: solving the guest room price under the maximum expected profit:
Figure BDA0002860936970000045
Figure BDA0002860936970000046
Figure BDA0002860936970000047
wherein the content of the first and second substances,
Figure BDA0002860936970000048
the optimal pricing is realized for each day of hotel rooms in the pre-sale period T.
A hotel room dynamic pricing device, comprising:
the data acquisition module is used for acquiring historical data of each room type of the hotel and processing the historical data to obtain historical data of the room price demand;
the price fitting module is used for fitting a price demand function based on the historical data of the guest room price demand and predicting the demands corresponding to different price points;
the model creating module is used for creating a dynamic game model of hotel room pricing and customer requirements based on a dynamic game theory;
the demand distribution module is used for making the highest price and the lowest price of the hotel rooms and obtaining the probability distribution of the order accepted by the customers according to the proportion of the highest price and the lowest price accepted by the customers;
and the pricing module is used for optimizing the profit model according to the probability distribution of the order received by the customer, the number of required guestrooms and the balanced solution of the dynamic game model, and solving to obtain the dynamic price of the hotel guestrooms in the pre-sale period.
A hotel room dynamic pricing device, comprising:
a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;
the at least one processor invokes the instructions in the memory to cause the hotel room dynamic pricing device to perform a hotel room dynamic pricing method in an embodiment of the invention.
A computer-readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing a method for dynamic pricing of hotel rooms in an embodiment of the invention.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects:
1) according to the hotel room dynamic pricing method in the embodiment of the invention, aiming at the problems that the traditional hotel often makes a decision on the pricing of rooms based on experience, which is generally limited by the work experience and the reading of a pricing person, and has strong subjectivity and can not effectively improve the income, historical data of each room type of the hotel is collected and processed to obtain the historical data of the room price requirement; fitting a price demand function based on the historical data of the guest room price demand to predict the demands corresponding to different price points; establishing a dynamic game model of hotel room pricing and customer requirements based on a dynamic game theory; setting the highest price and the lowest price of a hotel room, and obtaining the probability distribution of the order accepted by the customer according to the ratio of the highest price and the lowest price accepted by the customer; and optimizing the profit model according to the probability distribution of the order received by the customer, the number of required guestrooms and the balanced solution of the dynamic game model, and solving to obtain the dynamic price of the hotel guestrooms in the pre-sale period. Therefore, the overall income of the hotel is effectively improved, and the problems of low income and insufficient competitiveness caused by pricing guest rooms according to experience in the traditional hotel industry are solved.
2) Aiming at the problem of right cut-off of the demand of the hotel caused by the limitation of the number of the rooms, the hotel room dynamic pricing method in the embodiment of the invention adopts a limited dependent variable regression method to restore the historical data to the un-cut-off state, removes the periodic and seasonal factors, processes the historical data into the demand data only depending on the price, and is convenient for fitting a price demand function and predicting the price of the remaining stock of the rooms.
Drawings
Fig. 1 is a flow diagram of a hotel room dynamic pricing method in an embodiment of the invention;
FIG. 2 is a comparison graph of the number of guest room reservations before and after truncation and restoration of historical data, in accordance with an embodiment of the present invention;
FIG. 3 is a comparison graph of the number of room reservations before and after a historical data stripping periodicity and seasonality factor in an embodiment of the present invention;
FIG. 4 is a graph of price demand in one embodiment of the present invention;
fig. 5 is a schematic diagram of a hotel room dynamic pricing device in an embodiment of the invention;
fig. 6 is a schematic diagram of a hotel room dynamic pricing device in an embodiment of the invention.
Detailed Description
The hotel room dynamic pricing method, the hotel room dynamic pricing device, the hotel room dynamic pricing equipment and the hotel room dynamic pricing storage medium provided by the invention are further described in detail with reference to the drawings and specific embodiments. Advantages and features of the present invention will become apparent from the following description and from the claims.
Example one
Dynamic pricing is part of revenue management, and means that an optimal price strategy is formulated by collecting historical data of customers and analyzing habits and characteristics of customer purchases. The dynamic pricing of the hotel rooms has very important significance on daily operation and income management of the hotel, the price of the hotel rooms most directly reflects the income condition of the hotel, the income and the profitability of the hotel can be further improved by adjusting the price of the hotel rooms, and the maximization of the total income is realized.
The embodiment provides a hotel room dynamic pricing method aiming at the problems that traditional hotels often make decisions based on experiences, the traditional hotels are generally limited by work experiences and reviews of pricing workers, the subjectivity is strong, and the total income cannot be effectively improved.
Referring to fig. 1, the method for dynamically pricing hotel rooms includes:
s1: collecting historical data of each room type of the hotel, and processing the historical data to obtain historical data of the price demand of the rooms;
s2: fitting a price demand function based on the historical data of the guest room price demand to predict the demands corresponding to different price points;
s3: establishing a dynamic game model of hotel room pricing and customer requirements based on a dynamic game theory;
s4: setting the highest price and the lowest price of a hotel room, and obtaining the probability distribution of the order accepted by the customer according to the ratio of the highest price and the lowest price accepted by the customer;
s5: and optimizing the profit model according to the probability distribution of the order received by the customer, the number of required guestrooms and the balanced solution of the dynamic game model, and solving to obtain the dynamic price of the hotel guestrooms in the pre-sale period.
Specifically, in step S1, in this embodiment, data of the type a in all types of rooms of a hotel from 7/2015 to 8/2017 is used as historical data of hotel orders, and is sorted into a predetermined number of rooms per day, a limited dependent variable regression method, such as a Tobit regression or multiple logistic regression model, is used to deal with the problem of right cutoff of demand caused by the limitation of the number of rooms, the historical data is restored to an untruncated state, the historical data of the hotel reservation per day is restored, and then seasonal factors are removed. The method comprises the following specific steps:
s11: for historical data, since the maximum predetermined number of rooms is the total number of rooms, but the real demand of the customer may be greater than the total number of rooms, when the predetermined number of rooms is maximum, corresponding to the demand of the customer, it is necessary to use a limited dependent variable regression method, to handle the problem of right truncation of the demand due to the limitation of the number of rooms, to restore the historical data to an un-truncated state, and to strip off periodic and seasonal factors.
For data points where demand is not truncated (original number of rooms <120), the original data is still used as the actual demand. For the data point with the truncated demand (the original preset number of guest rooms is 120), if the fitting value of the Tobit regression model is less than 120, the original data is still used as the actual demand, and if the fitting value of the Tobit regression model is greater than 120, the fitting value of the Tobit regression model is used as the actual demand, and the actual demand and the data which is not truncated are combined to obtain the truncated and reduced number of the preset guest rooms.
The restricted dependent variable regression method may be a Tobit regression, or a multivariate logistic regression or other model. In the embodiment, the Tobit regression is adopted to process the problem of right truncation of the demand caused by the limitation of the number of guest rooms, and the historical data is restored to be in an untruncated state.
The Tobit regression model is used for data with dependent variable being partially continuous and partially discrete distribution. The basic model is as follows:
y*＝β′xi+ui，
Figure BDA0002860936970000071
Figure BDA0002860936970000072
wherein the content of the first and second substances,
Figure BDA0002860936970000073
is a dependent variable (i.e., the number of guest rooms) which is observed when the dependent variable is greater than 0 and takes the value yi(ii) a When the dependent variable is less than or equal to 0, the value is 0; x is the number ofiIs an argument vector; β' is a coefficient vector; u. ofiIs an error term that is independent and obeys a positive power distribution: u. ofi～N(0，σ2)。
The values of the parameters β' and σ of the Tobit regression model can be obtained by maximum likelihood estimation, which is not described in detail herein.
Referring to fig. 2, the number of the guest room reservations before and after the truncation of the historical data is compared, in which a solid line represents a data curve of the demand truncation and a dotted line represents a curve after the restoration of the demand truncation point. From the figure, it can be easily seen that the curve after the requirement truncation and restoration is not limited to the value of 120 any more, the historical requirement data is restored to the state without truncation, and the real effectiveness of the requirement data is improved.
And calculating corresponding week factors, ten-day factors and month factors according to the reduced truncated data, and removing the influence of periodic and seasonal factors. The method comprises the following specific steps:
s12: solving main periodic and seasonal factor factors including a week factor, a ten-day factor and a month factor;
wherein, the calculation formula of each factor is as follows:
week factor:
Figure BDA0002860936970000081
factor of ten days:
Figure BDA0002860936970000082
monthly factor:
Figure BDA0002860936970000083
the formula of the demand after stripping off the seasonal factors is as follows:
Figure BDA0002860936970000084
wherein the content of the first and second substances,
Figure BDA0002860936970000085
and
Figure BDA0002860936970000086
respectively the average requirements of each week, each ten-day and each month in the historical data;
Figure BDA0002860936970000087
is the overall average demand;
Figure BDA0002860936970000088
to cut off the demand after reduction.
Wti、EtjAnd MtkAll values are between 0 and 1 and satisfy
Figure BDA0002860936970000089
And
Figure BDA00028609369700000810
if the day of residence t is on day i of the week, WtiOtherwise, Wti0; if the ten-day degree of the entering date t is j, Etj1, otherwise Etj0; if the month of the entering-living day t is k, Mtk1, otherwise Mtk＝0。
Referring to fig. 3, the solid line represents the raw data curve (i.e., the data curve without stripping the periodic and seasonal factors), and the dashed line represents the data curve after stripping the periodic and seasonal factors. After the periodic and seasonal factors of the demand data are stripped, compared with the guest room booking number without stripping the periodic and seasonal factors, the guest room booking number reduces the fluctuation range of the data, and the demand data tends to be stable.
Step S2 further includes: based on the historical data of the guest room price demand, a local slope updating algorithm or a least square method is adopted to fit a price demand function.
In the embodiment, the reduced demand data set is used as a sample set, the demand data from 2017 to 2017 and month 4 to 8 is selected as historical data, and a local slope updating method is used for fitting a price demand curve in the house type pre-sale period, wherein the house type pre-sale period is 10 days in 2017 and 9 months in a check-in date and ten days in a pre-sale period. The method comprises the following specific steps:
in the local slope updating method, according to Lagrange's median theorem, when the price variation interval is sufficiently small, the slope of the price demand function obtained at a certain price point can be approximately used as the unified slope value of the interval near the price point.
The specific steps of local slope update are as follows:
obtaining selected historical scattered points, wherein the scattered points are real sample points and correspond to price requirements (pi, di), and i is 1, 2, 3 …
A demand function D1 (-) with a first segment slope of-D1/p 1 is obtained from a first sample point (p1, D1) (the slope of the price demand in a cell around this point is determined by this point, and the slope represents a price sensitivity or price elasticity).
The second sample point (p2, D2) obtains a demand function D2 (-) with a second segment slope of-D2/p 2, and the previous first segment is adjusted (slope is constant and intercept is changed) to ensure that price sensitivity among each cell is determined by the nearest sample point and continuity of the whole demand function.
By analogy, the t-th section of the demand curve is obtained at the t-th sample point, and meanwhile, the previous t-1 section is adjusted, and finally, the price demand curve in the house type pre-sale period based on historical data is obtained:
Figure BDA0002860936970000091
the price demand curve is shown in fig. 4.
Step S3 further includes: in the dynamic game model, the game of the hotel and the customer about the price of the guest room is a non-antagonistic cooperative game, the hotel and the customer conspire to jointly obtain the benefit as much as possible, and the ideal outcome pursued by the hotel is that the benefit of the hotel is as much as possible on the basis of the reservation of the customer.
When a dynamic game model is created, a hotel can firstly set the pre-sale price of a guest room and then generate two different prediction benefits according to the feedback result of reservation or non-reservation of customers; according to the income prediction result, the decision of the hotel is to adjust the pre-sale price of the guest room on the premise of customer reservation.
Dynamic gambling refers to the sequential order of the participants' actions, and the latter can observe the selection of the former and make corresponding selections based on the observed selection. Specifically to the present embodiment, the participants in the dynamic game are hotel pricing providers and customers. A hotel pricing person firstly makes a pre-sale price of a guest room, a customer compares the pre-sale price with a psychological expectation, and if the customer is within the psychological expectation (acceptable price), the hotel pricing person makes a reservation; if it is not psychologically expected (unacceptable price), it is not booked.
Step S4 further includes:
s41: the maximum price f of the guest room is set according to the actual condition of the hotelmax；
S42: according to the fitted price demand function in step S2, check-inThe price corresponding to the actual remaining stock of the guest room is taken as the lowest price fmin；
S43: calculating the maximum acceptable guest room price f through historical datamaxThe customer ratio of (a) is θ;
Figure BDA0002860936970000101
s44 the probability distribution from the guest room to the customer accepting the guest room price to order is:
Figure BDA0002860936970000102
in this embodiment, the maximum price and the minimum price in the pre-sale period of the house type of the hotel are set for the day of 9 and 1 month in 2017, and the probability distribution of the customer receiving the pre-sale order in the pre-sale period is obtained according to the ratio of the maximum price and the minimum price received by the customer, which is specifically as follows:
the maximum price of the guest room is set to be 250 through the non-discount price of the guest room, and the price 128 corresponding to the actual remaining stock of the guest room with the number of the incoming days of 2017, 9 and 10 in 9 and 1 in 2017 is found out from the fitted demand function and serves as the minimum price.
Calculating the maximum acceptable guest room price f through the historical data of the customer's room reservation from 4 to 8 months in 2017maxThe customer ratio of (a) is:
Figure BDA0002860936970000103
when the probability distribution of the hotel room price booking of the guest room is calculated, the probability distribution function is assumed to be epsilon (x) as ax + b, and epsilon (f) is substitutedmax)＝θ，ε(fmin) 1, obtaining:
ε(x)＝2.28-0.01x
step S5 further includes:
s51: fitting the Poisson distribution of the number of the required guest rooms in the pre-sale period according to the annual data of the number of the required guest rooms in the historical data:
Figure BDA0002860936970000111
wherein the intensity lambdatThe number of the required guest rooms is the number of the required guest rooms per day in the pre-sale period;
s52: the revenue function of each guest room in the pre-sale period of the hotel is as follows:
Figure BDA0002860936970000112
wherein
Figure BDA0002860936970000113
The optimal price of the current day of guest rooms of the hotel in the pre-sale period is set;
s53: the expected revenue of each day of the guest room during the pre-sale period of the hotel is:
Figure BDA0002860936970000114
s54: solving the guest room price under the maximum expected profit:
Figure BDA0002860936970000115
Figure BDA0002860936970000116
Figure BDA0002860936970000117
wherein the content of the first and second substances,
Figure BDA0002860936970000118
the optimal pricing is realized for each day of hotel rooms in the pre-sale period T.
The optimal expected income algorithm is established according to the probability distribution of the order received by the customer, the number of people required by the guest room and the equilibrium solution of the dynamic game model, and the optimal dynamic price of the hotel in the pre-sale period is obtained through solving, and the method specifically comprises the following steps:
acquiring annual guest room demand number data through historical data, and fitting Poisson distribution according to the data:
Figure BDA0002860936970000119
obtaining the Poisson intensity lambda of each day in the pre-sale periodt＝{4，6，8，8，10，12，14，16，18，20}。
According to the optimal dynamic price under the maximum expected income solving:
Figure BDA0002860936970000121
Figure BDA0002860936970000122
Figure BDA0002860936970000123
the optimal price per day during the pre-sale period is obtained:
Figure BDA0002860936970000124
the benefits of using the dynamic pricing model for the same type of room are compared as shown in the following table:
the remaining pre-sale period (day) Empirical pricing Dynamic model pricing
10 160 144
9 170 147
8 180 149
7 190 149
6 200 151
5 210 153
4 220 155
3 230 157
2 240 158
1 250 170
Guest room sales volume (room) 80 120
Hotel gain (Wanyuan) 1.64 1.84
It can be seen that without considering the cost of the hotel, pricing using the dynamic pricing model increases the sales volume of the guest rooms and improves the revenue of the hotel, although the price is not as high as the hotel pricing staff passes the experience.
Example two
The embodiment provides a hotel room dynamic pricing device, please refer to fig. 5, the device includes:
the data acquisition module 1 is used for acquiring historical data of each room type of the hotel and processing the historical data to obtain historical data of the room price demand;
the price fitting module 2 is used for fitting a price demand function based on the historical data of the guest room price demand and predicting the demands corresponding to different price points;
the model creating module 3 is used for creating a dynamic game model of hotel room pricing and customer requirements based on a dynamic game theory;
the demand distribution module 4 is used for making the highest price and the lowest price of the hotel rooms and obtaining the probability distribution of the order accepted by the customers according to the proportion of the highest price and the lowest price accepted by the customers;
and the pricing module 5 is used for optimizing the profit model according to the probability distribution of the order received by the customer, the number of required guestrooms and the balanced solution of the dynamic game model, and solving to obtain the dynamic price of the hotel guestrooms in the pre-sale period.
The functions and implementation methods of the data acquisition module 1, the price fitting module 2, the model creation module 3, the demand distribution module 4, and the pricing module 5 are all consistent with the description of the first embodiment, and are not described herein again.
EXAMPLE III
In the second embodiment, the hotel room dynamic pricing device is described from the perspective of the modular functional entity, and the hotel room dynamic pricing device is described in detail from the perspective of hardware processing.
Referring to fig. 6, the hotel room dynamic pricing device 500 may vary greatly due to different configurations or capabilities, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and memory 520, one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instructions operating on the hotel room dynamic pricing device 500.
Further, processor 510 may be configured to communicate with storage medium 530 to execute a series of instruction operations in storage medium 530 on hotel room dynamic pricing device 500.
The hotel room dynamic pricing device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows server, Vista, and the like.
Those skilled in the art will appreciate that the hotel room dynamic pricing equipment configuration shown in figure 6 does not constitute a limitation of the hotel room dynamic pricing equipment and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium. The computer-readable storage medium has stored therein instructions, which when executed on a computer, cause the computer to perform the steps of the hotel room dynamic pricing method of the first embodiment.
The modules in the second embodiment, if implemented in the form of software functional modules and sold or used as independent products, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be substantially or partially implemented in software, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and devices may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments. Even if various changes are made to the present invention, it is still within the scope of the present invention if they fall within the scope of the claims of the present invention and their equivalents.

Claims (10)

1. A hotel room dynamic pricing method is characterized by comprising the following steps:
s1: collecting historical data of each room type of the hotel, and processing the historical data to obtain historical data of the price demand of the rooms;
s2: fitting a price demand function based on the historical data of the guest room price demand to predict the demands corresponding to different price points;
s3: establishing a dynamic game model of hotel room pricing and customer requirements based on a dynamic game theory;
s4: setting the highest price and the lowest price of a hotel room, and obtaining the probability distribution of the order accepted by the customer according to the ratio of the highest price and the lowest price accepted by the customer;
s5: and optimizing the profit model according to the probability distribution of the order received by the customer, the number of required guestrooms and the balanced solution of the dynamic game model, and solving to obtain the dynamic price of the hotel guestrooms in the pre-sale period.
2. The hotel room dynamic pricing method of claim 1, wherein the step S1 further comprises:
s11: a limited dependent variable regression method is used for processing the problem of right truncation of the demand caused by the limitation of the number of guest rooms, the historical data is restored to be in an untruncated state, and periodic and seasonal factors are stripped;
s12: solving main periodic and seasonal factor factors including a week factor, a ten-day factor and a month factor;
wherein, the calculation formula of each factor is as follows:
week factor:
Figure FDA0002860936960000011
factor of ten days:
Figure FDA0002860936960000012
monthly factor:
Figure FDA0002860936960000013
the formula of the demand after stripping off the seasonal factors is as follows:
Figure FDA0002860936960000014
wherein the content of the first and second substances,
Figure FDA0002860936960000015
and
Figure FDA0002860936960000016
respectively the average requirements of each week, each ten-day and each month in the historical data;
Figure FDA0002860936960000017
is the overall average demand;
Figure FDA0002860936960000018
to cut off the demand after reduction.
Wti、EtjAnd MtkAll values are between 0 and 1 and satisfy
Figure FDA0002860936960000019
And
Figure FDA0002860936960000021
3. the hotel room dynamic pricing method of claim 2, wherein the step S11 further comprises: and (3) adopting a Tobit regression or multiple logistic regression model to process the problem of right truncation of the demand caused by the limitation of the number of guest rooms and restore the historical data into a non-truncated state.
4. The hotel room dynamic pricing method of claim 1, wherein the step S2 further comprises:
based on the historical data of the guest room price demand, a local slope updating algorithm or a least square method is adopted to fit a price demand function.
5. The hotel room dynamic pricing method of claim 1, wherein the step S3 further comprises:
in the dynamic game model, the game of the hotel and the customer about the guest room pricing is a non-antagonistic cooperative game; in the process of establishing the dynamic game model, a hotel firstly makes a pre-sale price of a guest room, and then generates two different prediction benefits according to a feedback result of reservation or non-reservation of a customer; obtaining decision selection of the hotel according to the income prediction result; and making a dynamic pricing model of the guest room based on decision selection of the hotel.
6. The hotel room dynamic pricing method of claim 1, wherein the step S4 further comprises:
s41: the maximum price f of the guest room is set according to the actual condition of the hotelmax；
S42: according to the fitted price demand function in the step S2, taking the price corresponding to the actual remaining stock of the guest room on the stay day as the minimum price fmin；
S43: calculating the maximum acceptable guest room price f through historical datamaxThe customer ratio of (a) is θ;
Figure FDA0002860936960000022
s44 the probability distribution from the guest room to the customer accepting the guest room price to order is:
Figure FDA0002860936960000023
7. the hotel room dynamic pricing method of claim 1, wherein the step S5 further comprises:
s51: fitting the Poisson distribution of the number of the required guest rooms in the pre-sale period according to the annual data of the number of the required guest rooms in the historical data:
Figure FDA0002860936960000031
wherein the intensity lambdatThe number of the required guest rooms on the t day;
s52: the revenue function of each guest room in the pre-sale period of the hotel is as follows:
Figure FDA0002860936960000032
wherein
Figure FDA0002860936960000033
The optimal price of the current day of guest rooms of the hotel in the pre-sale period is set;
s53: the expected revenue of each day of the guest room during the pre-sale period of the hotel is:
Figure FDA0002860936960000034
s54: solving the guest room price under the maximum expected profit:
Figure FDA0002860936960000035
Figure FDA0002860936960000036
Figure FDA0002860936960000037
wherein the content of the first and second substances,
Figure FDA0002860936960000038
the optimal pricing is realized for each day of hotel rooms in the pre-sale period T.
8. A hotel room dynamic pricing device, comprising:
the data acquisition module is used for acquiring historical data of each room type of the hotel and processing the historical data to obtain historical data of the room price demand;
the price fitting module is used for fitting a price demand function based on the historical data of the guest room price demand and predicting the demands corresponding to different price points;
the model creating module is used for creating a dynamic game model of hotel room pricing and customer requirements based on a dynamic game theory;
the demand distribution module is used for making the highest price and the lowest price of the hotel rooms and obtaining the probability distribution of the order accepted by the customers according to the proportion of the highest price and the lowest price accepted by the customers;
and the pricing module is used for optimizing the profit model according to the probability distribution of the order received by the customer, the number of required guestrooms and the balanced solution of the dynamic game model, and solving to obtain the dynamic price of the hotel guestrooms in the pre-sale period.
9. A hotel room dynamic pricing device, comprising:
a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;
the at least one processor invokes the instructions in the memory to cause the hotel room dynamic pricing device to perform the hotel room dynamic pricing method of any of claims 1-7.
10. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method for dynamic pricing of hotel rooms as recited in any of claims 1-7.
CN202011565991.XA 2020-12-25 2020-12-25 Hotel guest room dynamic pricing method, device, equipment and storage medium Pending CN112734457A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011565991.XA CN112734457A (en) 2020-12-25 2020-12-25 Hotel guest room dynamic pricing method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011565991.XA CN112734457A (en) 2020-12-25 2020-12-25 Hotel guest room dynamic pricing method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112734457A true CN112734457A (en) 2021-04-30

Family

ID=75616456

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011565991.XA Pending CN112734457A (en) 2020-12-25 2020-12-25 Hotel guest room dynamic pricing method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112734457A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115953268A (en) * 2023-01-04 2023-04-11 广州辰亿信息科技有限公司 Hotel data processing system based on big data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020116348A1 (en) * 2000-05-19 2002-08-22 Phillips Robert L. Dynamic pricing system
WO2007130527A2 (en) * 2006-05-02 2007-11-15 Vendavo, Inc. Systems and methods for business to business price modeling using price elasticity optimization
WO2008060507A1 (en) * 2006-11-13 2008-05-22 Vendavo, Inc. Systems and methods for price optimization using business segmentation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020116348A1 (en) * 2000-05-19 2002-08-22 Phillips Robert L. Dynamic pricing system
WO2007130527A2 (en) * 2006-05-02 2007-11-15 Vendavo, Inc. Systems and methods for business to business price modeling using price elasticity optimization
WO2008060507A1 (en) * 2006-11-13 2008-05-22 Vendavo, Inc. Systems and methods for price optimization using business segmentation

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
周蔷等: "基于博弈理论的航空机票动态定价模型", 《江苏大学学报(自然科学版)》 *
陈吉等: "基于局部斜率更新的数据驱动动态定价策略", 《***工程学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115953268A (en) * 2023-01-04 2023-04-11 广州辰亿信息科技有限公司 Hotel data processing system based on big data
CN115953268B (en) * 2023-01-04 2024-05-24 广州辰亿信息科技有限公司 Hotel data processing system based on big data

Similar Documents

Publication Publication Date Title
Diewert et al. Substitution bias in multilateral methods for CPI construction using scanner data
Cottet et al. Bayesian modeling and forecasting of intraday electricity load
Ziarnetzky et al. Rolling horizon, multi-product production planning with chance constraints and forecast evolution for wafer fabs
US20150227859A1 (en) Systems and methods for creating a forecast utilizing an ensemble forecast model
Chambers et al. Participation in the farmer-owned reserve program: a discrete choice model
US20140310059A1 (en) System , method and computer program forecasting energy price
Khouja et al. A multi-product constrained newsboy problem with progressive multiple discounts
CA2788266A1 (en) Inventory management and budgeting system
CN108156204B (en) Target object pushing system and method
WO2001097135A2 (en) Event revenue management system
DE10257199A1 (en) Optimized pricing plan generation method for business items, involves determining mathematical model comprising set of initial constraints, and representing pricing plan for group of item
US11360999B2 (en) Computer-implemented method for managing inventory allocations
CN112529333A (en) Prediction method, device, equipment and storage medium for overdesigned number of hotel rooms
CN113344282B (en) Method, system and computer readable medium for capacity data processing and allocation
CN112734457A (en) Hotel guest room dynamic pricing method, device, equipment and storage medium
Dhuyvetter et al. Forecasting crop basis: Practical alternatives
Zenkova et al. Accounting for deficit in ABC-XYZ analysis
JP4296026B2 (en) Product demand forecasting system, product sales volume adjustment system
CN117217804A (en) Intelligent pricing and inventory management method and system
Heer Employment and welfare effects of a two-tier unemployment compensation system
Schulhofer-Wohl Heterogeneous risk preferences and the welfare cost of business cycles
CN115689222A (en) Material scheduling method and construction site material management system based on Internet of things
JP2019046467A (en) Power transaction support device and power transaction support method
CN114742657A (en) Investment target planning method and system
US20210073840A1 (en) Multi-layered system for heterogeneous pricing decisions by continuously learning market and hotel dynamics

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210430