線上訂位是現代在地化服務的主要客戶來源，準確的預測線上訂位需求量對於服務提供者而言，能提供更好的顧客服務與更有效率的配置資源。我們希望利用東南亞最大餐廳訂位服務網站EZTABLE的每週線上訂位資料。由於餐廳訂位量會因為節日、假期或是其他特殊事件而有強烈的影響，我們研究不同獲取這些資訊的方法來準確預測非特殊事件的時間。主要研究訂位資料預測的文獻大都是以飯店訂位為主，且運用各個不同的飯店分別的預測各自的需求。我們發展一種有用的方法給擁有大量服務提供者（如餐廳或飯店）資料的線上平台。特別的是，我們利用不同且多個的餐廳建模來預測個別餐廳訂位。我們聚焦於如何辨識特殊事件的週期，並利用不同的方法來分別建模以解決預測以週為單位的訂位時會遭遇特殊事件發生時異常訂位量的挑戰。其他挑戰包含以週為單位的預測、複雜季節性問題和餐廳不同的策略等。我們發展並比較幾個方法，包含利用日曆、利用單一餐廳的歷史資料和利用學習多個餐廳資料來解決這些面臨的挑戰。

Online bookings are major inputs to modern local businesses. Accurate forecasts of online booking demand are crucial for service providers to provide better customer services and allocate resources more efficiently. We develop a forecasting procedure for forecasting time series of weekly online restaurant bookings, using data from EZTABLE, the biggest online booking platform in southeast Asia. Because restaurant demand is greatly impacted by holidays and other special occasions, we study different possibilities of capturing such information to achieve accurate forecasts on non-special periods. The literature on forecasting bookings is mostly about hotel reservations, where the time series of bookings for each hotel are considered separately. We develop a method that is useful for platforms that have data on many service providers (such as many restaurants or hotels). In particular, we generate forecasts for each restaurant’s reservations by creating models that use data from other restaurants. We focus on how to identify special weeks so that they can be modeled separately, and use different approaches to solve challenges that arise in forecasting weekly reservations data for many restaurants in the presence of unusual demand on special weeks. These challenges include the weekly frequency of forecasting, complex seasonality, and restaurant strategies. We develop and compare several approaches, including using calendar dates, using historic data from a single restaurant, and learning from multiple restaurants.

Chapter 1 Introduction 1
1.1 Background and motivation 1
1.2 Data and analytics usage by online platforms 2
1.3 Research question 3
1.4 Case Study: Forecasting online restaurant bookings 3
Chapter 2 Forecasting Booking Demand 7
2.1 Forecasting methods for bookings 7
2.2 Definition of booking date and reservation date 10
Chapter 3 Challenges of Forecasting Weekly Booking Demand 12
3.1 Frequency of forecasting: The challenge of weekly data 12
3.2 Complex seasonality: The challenge of dual-calendar 13
3.3 Restaurant strategy: The challenge of setting online booking capacity 14
Chapter 4 Visualization and Preparation 15
4.1 The forecasting tools: Modeling and visualization 15
4.2 Data preprocessing 16
Chapter 5 Approaches of Forecasting Reservation Demand 19
5.1 Training set 19
5.2 Independent restaurant approach 19
5.3 Dependent restaurant approach 23
Chapter 6 Comparison of Independent and Dependent Approaches 30
Chapter 7 Directions 38
References 40
Appendices 42
A.1 R code for two-step model 42
A.2 R code for non-holiday series 43

Box, G.E.P. & Jenkins, G.M. (1970). Time series Analysis: forecasting and control. San Francisco : Holden-Day .
Robert, B.G. & Richard, M.F. (1961, October). The Fundamental Theorem of Exponential Smoothing. Operations Research, 9 (5), 673-687.
Lin, C.F. (2009, October). Forecasting tourism demand with ARMA-based methods. Tourism Management, 30 (5), 740-751.
Harvey Andrew, Koopman Jan Siem, & Riani Marco. (1997, July). The Modeling and Seasonal Adjustment of Weekly Observations. Journal of Business & Economic Statistics, 15 (3), 354-368.
Rob, H.J. & Yeasmin, K. (2008, July). Automatic Time Series Forecasting: The forecast Package for R. Journal of Statistical Software, 27 (3).
Ismail, Z., Jamaluddin, F. & Jamaludin, F. (2008, January). Time Series Regression Model for Forecasting Malaysian Electricity Load Demand. Asian Journal of Mathematics and Statistics, 1 (3), 139-149.
Lin, T. & Tsai, C.C. (2015, November). A Simple Linear Regression Approach to Modeling and Forecasting Mortality Rates. Journal of forecasting, 34 (7), 543-559.
Alysha, L.M.D, Rob, H.J. & Ralph, S.D. (2011). Forecasting time series with complex seasonal patterns using exponential smoothing. Journal of the American Statistical Association, 106 (496), 1513-1527.
Peng, Z., Yu, Z., Wang. H. & Yang, S. (2015, February). Research on Industrialization of Electric Vehicles with its Demand Forecast Using Exponential Smoothing Method. Journal of Industrial Engineering and Management, 8 (2), 365-382.
Larry, W.R. & Sheryl, K.E. (2003, July-September). A comparison of forecasting methods for hotel revenue management. International Journal of Forecasting, 19 (3), 401-415.
Athanasius, Z., Neamat, G.E. & Amir, A.F. (2011, June). A Comparative Study of the Pickup Method and its Variations Using a Simulated Hotel Reservation Data. ICGST-AIML Journal, 8, 15-21.