Boosting Hotel Profits: The Power of Enhanced Cancellation Predictions

2024/06/30-7/3実施の EURO 2024で発表した、木村の資料です。

Transcript

1. Boosting Hotel Profits: The Power of Enhanced Cancellation Predictions Ryusuke Kimuraa, Kimitoshi Satob a Data Management & Planning Office, Recruit Co., Ltd. b Facluty of Engineering, Kanagawa University 33rd European Conference on Operational Research 30th June – 3rd July 2024, Copenhagen, Denmark
2. Agenda 1. Introduction 2. Simulation Settings 3. Numerical Examples 4. Conclusion and Future Work
3. 1. Introduction Our company started in the human resources field, but we provide matching platforms in various areas including the travel sector in Japan 󰏦
4. 1. Introduction Our company offers matching platform called jalan.net for hotel industry 🏨
5. 1. Introduction We also provide support for back office revenue management tasks by offering service called Revenue Assistant 📊 ✅KPI dashboards (OCC, ADR, booking curve) ✅Price suggestion ✅Anomaly detection
6. 1. Introduction Cancellation management is crucial in various tasks in hotel industry🏨 Ordering food ingredients and amenities 🍖 Shift scheduling for staffs 🗓 Revenue Management 📊
7. 1. Introduction The key to cancellation management is predicting cancellations accurately💡 Prediction 📈 Actual 🗓 2 out of 6 bookings will predicted to be canceled 4 out of 6 bookings are canceled
8. 1. Introduction There are existing studies on cancellation prediction in hotels 📗 # Aim of research Paper 1 Create high accuracy cancellation prediction model Dolores Romero Morales, Jingbo Wang, Forecasting cancellation rates for services booking revenue management using data mining, European Journal of Operational Research 202 (2010) 554–562 [Paper] Nuno Antonio, Ana de Almeida, Luis Nunes, Predicting hotel booking cancellations to decrease uncertainty and increase revenue, Tourism & Management Studies, 13(2), 2017 [Paper] 2 A/B testing of the effect of contacting customers based on cancellation prediction Nuno Antonio, Ana de Almeida, Luis Nunes, Predicting Hotel Bookings Cancellation With a Machine Learning Classification Model, 2017 16th IEEE Conference on Machine Learning and Applications, 2017 [Paper] 3 Data article - describing two hotel datasets Nuno Antonio, Ana de Almeida, Luis Nunes, Hotel booking demand datasets, Data in Brief Volume 22, February 2019, Pages 41-49 [Paper, Kaggle, Kaggle Notebook]
9. 1. Introduction However, from a hotel's perspective, following questions are not answered yet 🤔 Question 1 Question 2 How much impact does improving the accuracy of cancellation prediction have on revenue growth?💰 In what situations does improving the accuracy of cancellation prediction have an impact on revenue growth?📈 To answer these questions, we conducted simulations using estimated parameters derived from real data of the hotel in Japan 🏨󰏦
10. Agenda 1. Introduction 2. Simulation Settings 3. Numerical Examples 4. Conclusion and Future Work
11. 2. Simulation Settings Assumption and Notations 💻 1. Hotel sells C units of perishable room over [0, T] 2. Selling price at time t : p t ∈ [p min , p max ] 3. Assumptions: a. The hotel has only one room type and one meal plan. b. At time t, only one reservation is accepted (no multiple or group bookings is accepted). Example of #1: The hotel has only double room with dinner and breakfast included. +
12. 2. Simulation Settings Assumption and Notations 💻 The model of dynamic pricing is extended by adding cancellations based on Bitran and Mondschein (1997). 1. Consumer arrives at arrival rate at time t : λ t 2. Consumer reserve the room with probability of Pr(X > p t ) 3. Cancellation rate at time t : γ t 4. Cancellation and its timing t + τ are determined at time t , where τ ∼ Pr(τ | t) 5. Cancellation refund percentage at time t + τ : r t + τ λ t reserve not reserve cancel not cancel Pr(X > p t ) Pr(X < p t ) γ t 1 - γ t arrive gain revenue at t : p t gain revenue at t + τ : p t (1-r t+τ )
13. 2. Simulation Settings Actual data of cancellation rate at time t : γ t 📊 leadtime t γ t (real values is confidential)
14. 2. Simulation Settings How to incorporate cancel prediction in the simulation 💻 1. Cancellation is predicted at time of reservation. 2. If a cancellation is predicted, reduce the inventory count by one. 3. If cancellation is predicted, keep the inventory unchanged. 4. A reservation determined to be canceled will result in an increase of one in inventory at time t + τ. λ t reserve not reserve cancel predicted cancel not predicted Pr(X > p t ) Pr(X < p t ) arrive reduce the inventory keep the inventory unchanged a t 1 - a t if reservation is determined to be canceled, increase one in inventory at time t + τ Probability that the cancel is predicted at time t
15. 2. Simulation Settings λ t reserve not reserve cancel predicted cancel not predicted Pr(X > p t ) Pr(X < p t ) arrive reduce the inventory keep the inventory unchanged a t 1 - a t if reservation is determined to be canceled, increase one in inventory at time t + τ Probability that the cancel is predicted at time t How to calculate a t 󰠁 1. a t is calculated based on the following components. - accuracy of the cancellation prediction model: acc - actual cancellation rate: γ a
16. 2. Simulation Settings How to calculate a t 󰠁 2. Numerical example. - if acc = 80% and γ a = 30%, a t 1 = 67%, a t 0 = 14%. - 1 in superscript of a t represents the occurrence of an actual cancellation, while 0 represents no actual cancellation. λ t reserve not reserve cancel predicted cancel not predicted Pr(X > p t ) Pr(X < p t ) arrive reduce the inventory keep the inventory unchanged a t 1 = 67% 1 - a t 1 = 33% if reservation is determined to be canceled, increase one in inventory at time t + τ
17. 2. Simulation Settings How to calculate a t 󰠁 2. Numerical example. - if acc = 80% and γ a = 30%, a t 1 = 67%, a t 0 = 14%. - 1 in superscript of a t represents the occurrence of an actual cancellation, while 0 represents no actual cancellation. λ t reserve not reserve cancel predicted cancel not predicted Pr(X > p t ) Pr(X < p t ) arrive reduce the inventory keep the inventory unchanged a t 0 = 14% 1 - a t 0 = 86% if reservation is determined to be canceled, increase one in inventory at time t + τ
18. 2. Simulation Settings How to calculate a t 󰠁 2. Numerical example. - if acc = 80% and γ a = 30%, a t 1 = 67%, a t 0 = 14%. - 1 in superscript of a t represents the occurrence of a cancellation, while 0 represents no cancellation. 3. We can derive a t based on confusion matrix of cancellation prediction model. - a t 1 = n TP / (n TP + n FN ) - a t 0 = n FP / (n FP + n TN ) Prediction Cancel Not Cancel Actual Cancel n TP n FN Not Cancel n FP n TN We need to calculate n TP , n FN , n FP , n TN in order to derive a t
19. 2. Simulation Settings How to calculate a t 󰠁 2. Numerical example. - if acc = 80% and γ a = 30%, a t 1 = 67%, a t 0 = 33%. - 1 in superscript of a t represents the occurrence of a cancellation, while 0 represents no cancellation. 3. We can derive a t based on confusion matrix of cancellation prediction model. - a t 1 = n TP / (n TP + n FN ) - a t 0 = n FP / (n FP + n TN ) Prediction Cancel Not Cancel Actual Cancel n TP n FN Not Cancel n FP n TN We need to calculate n TP , n FN , n FP , n TN in order to derive a t
20. 2. Simulation Settings How to calculate a t 󰠁 4. How to calculate n TP , n FP , n FN , n TN from acc - We assume that the actual cancellation rate γ a equals to the predicted cancellation rate γ p - n FP = n FN = N × (1 - acc) / 2 - γ a = γ p ⇒ (n TP + n FN ) / N = (n TP + n FP ) / N ⇒ n FN = n FP - n TP = N × (γ a - (1 - acc) / 2) - γ a = (n TP + n FN ) / N ⇒ n TP = N × γ a - n FN - n TN = N × ((1 - γ a ) - (1 - acc) / 2) - 1 - γ a = (n FP + n TN ) / N ⇒ n TN = N × (1 - γ a ) - n FP
21. 2. Simulation Settings The expected revenue from period t onwards, given an initial inventory of c 💰 v(t, c) = λ t Pr(X > p t ) (1 - γ t ) (p t (1 - ρ t )+ V(t + 1, c - 1)) When the customer arrives, makes a purchase, and does not cancel. + λ t Pr(X > p t ) γ t (p t + V(t + 1, c - 1)) When the customer arrives, makes a purchase, and cancels. + λ t Pr(X < p t )V(t + 1, c) When the customer arrives and does not make a purchase. + (1 - λ t )V(t + 1, c) When the customer does not arrive. where ρ t is expected refund ratio.
22. 2. Simulation Settings Value function The objective is to find the optimal price: V(t, c) = max v(t, c), c ∈ { 0, … , C }, t = 1, … , T where the boundary conditions are ... V(t, 0) = 0 When the inventory level reaches zero, the total expected revenue is zero. V(T+1, c) = 0 If there is remaining stock at the end of the sales period, the total expected revenue is zero. p t ∈ [p min , p max ]
23. Agenda 1. Introduction 2. Simulation Settings 3. Numerical Examples 4. Conclusion and Future Work
24. 3. Numerical Examples Parameters for the simulation 💻 1. Discretize the time interval [0, 1] into L = 60 periods. 2. Customer’s willingness to pay. a. Purchase probability: Pr(X > p t ) b. Probability distribution follows nonparametric distribution estimated from actual data. 3. Capacity: C = 7 4. Number of potential customers: 20 5. Cancellation rate γ t is calculated based on 7-period moving average of actual cancellation rate. 6. Cancellation timing of reservation at time t + τ follows nonparametric distribution estimated from actual data. 7. Cancellation refund percentage r t is determined by the cancellation policy of the actual property. 8. Simulate 10,000 sample paths and calculate their means. 9. Revenue is simulated at cancellation prediction accuracy ranging from [0.5, 1.0] in increments of 0.1
25. 3. Numerical Examples Simulation results for answering research question 💡 Question 1 Answer How much impact does improving the accuracy of cancellation prediction have on revenue growth? Accuracy of the cancellation prediction model improves by 10%, it will lead to an average revenue increase of 2%.
26. 3. Numerical Examples When the accuracy of the cancellation prediction model improves, an associated increase in revenue can be observed 📈
27. 3. Numerical Examples We also show that this improvement simultaneously improves consumer surplus by lowering the average sales price and improves the load factor📈
28. 3. Numerical Examples Simulation results for answering research question 💡 Question 2 Answer 2 In what situations does improving the accuracy of cancellation prediction have an impact on revenue growth? The higher the arrival rate, the greater the impact on improving accuracy.
29. 3. Numerical Examples We simulated the increase in revenue by multiplying the estimated arrival rates by values ranging from 0.1 to 3.0 and checked for variations in accuracy💡 The values multiplied by arrival rates 0.1 0.2 0.5 1.0 1.5 2.0 3.0 Accuracy 0.5 0.6 0.7 0.8 +X% 0.9 1.0 Revenue improvement ratio
30. 3. Numerical Examples The higher the arrival rate, the greater the impact on revenue improvement due to the increased accuracy of the cancellation prediction model 📈
31. Agenda 1. Introduction 2. Simulation Settings 3. Numerical Examples 4. Conclusion and Future Work
32. 4. Conclusion and Future Work Conclusion 1. We quantitatively evaluated the revenue increase from improving the accuracy of cancellation prediction model. 2. We found that accuracy improvement has a significant impact, especially for hotels with high arrival rates. High arrival rates
33. 4. Conclusion and Future Work Future Work 1. Evaluating the impact of accuracy improvements on revenue increase in relation to implementation of overbooking, and the presence of group reservation, and the difference in cancel policies, and the frequency of cancellations. 2. Evaluating the revenue increase from improving the estimation of arrival rates and willingness to pay function. Willingness to pay function Arrival rates
34. Appendix
35. Abstracts - Call for abstracts The hotel industry faces the uncertainty of reservations and cancellations. Although dynamic pricing provides appropriate discounts for last-minute cancellations, it is not always possible to fill vacancies unless there is sufficient demand. Therefore, it is important to know how the accuracy of cancellation forecasts affects the results of dynamic pricing in practice. In this study, we analyze the relationship between forecast accuracy and expected returns using actual data on room reservations and cancellations in a region in Japan. The results show that a 10% improvement in forecast accuracy results in a 2% improvement in revenue. We also show that this improvement simultaneously improves consumer surplus by lowering the average sales price and improves the load factor. Furthermore, the improvement is more effective during the peak season when the number of potential customers is higher.