Modeling daily guest count prediction

Fok Ricky; Lasek Agnieszka; Li Jiye; An Aijun

doi:10.3934/bdia.2016012

Article Contents

2016, Volume 1, Issue 4: 299-308. Doi: 10.3934/bdia.2016012

This issue Previous Article Analyzing opinion dynamics in online social networks Next Article A testbed to enable comparisons between competing approaches for computational social choice

Modeling daily guest count prediction

Department of Computer Science and Engineering York University 4700 Keele Street, Toronto, Ontario M3J 1P3, Canada

* Corresponding author: Ricky Fok
* Corresponding author: Ricky Fok

Published: September 2017

Abstract Full Text(HTML) Figure(3) / Table(1) Related Papers Cited by

Abstract

We present a novel method for analyzing data with temporal variations. In particular, the problem of modeling daily guest count forecast for a restaurant with more than 60 chain stores is presented. We study the transaction data collected from each store, perform data preprocessing and feature constructions for the data. We then discuss different forecasting techniques based on data mining and machine learning techniques. A new modeling algorithm SW-LAR-LASSO is proposed. We compare multiple regression model, poisson regression model, and the proposed SW-LAR-LASSO model for prediction. Experimental results show that the approach of combining sliding windows and LAR-LASSO produces the best results with the highest precision. This approach can also be applied to other areas where temporal variations exist in the data.

Keywords:

Mathematics Subject Classification: Primary:58F15, 58F17;Secondary:53C35.

Citation:

FullText(HTML)

Figure 1. Examples of boxplots for some of the stores from the chain of restaurants

Download: Full-size image PowerPoint slide

Figure 2. Three iterations of the sliding window are shown. Each line interval denotes a week. The shaded boxes denote the sliding windows for the training data over eight weeks and the empty boxes denote the weeks where the guest counts are predicted

Download: Full-size image PowerPoint slide

Figure 3. Experimental process for guest count predictions

Download: Full-size image PowerPoint slide

Table 1. Table of results from chosen stores. The bolded results denote the lowest predictive error among the three algorithms tested

Benchmark Stores	Multiple regression	Poisson regression	SW-LAR-LASSO	localization
Store_1	7.88	8.28	8.40	Canada stores
Store_2	15.56	16.71	15.00
Store_3	10.20	10.86	10.25
Store_4	13.15	14.51	12.86
Store_5	10.50	11.44	10.25
Store_6	16.04	17.66	14.19	US Stores
Store_7	18.62	24.37	15.60
Store_8	16.02	15.69	12.89
Store_9	--	--	22.57
Store_10	--	--	14.68

| Show Table

DownLoad: CSV

Related Papers

Cited by

References

[1]	S. Coxe, S. West and L. S. Aiken, The analysis of count data: A gentle introduction to poisson regression and its alternatives, J. Pers. Assess, 91 (2009), 121-136. doi: 10.1080/00223890802634175.
[2]	B. Efron, T. Hastie, I. Johnstone and R. Tibshirani, Tibshirani, Least angle regression, The Annals of Statistics, 32 (2004), 407-499. doi: 10.1214/009053604000000067.
[3]	F. G. Forst, Forecasting restaurant sales using multiple regression and box-jenkins analysis, J. Appl. Bus. Res, 382 (1992), 2157-8834. doi: 10.19030/jabr.v8i2.6157.
[4]	T. Hastie, R. Tibshirani and J. Friedman, The Elements of Statistical Learning, Data Mining, Inference, and Prediction, Springer Series in Statistics, Springer, New York, (2009). doi: 10.1007/978-0-387-84858-7.
[5]	S. E. Kimes, R. B. Chase, S. Choi, P. Y. Lee and E. N. Ngonzi, Restaurant revenue management applying yield management to the restaurant industry, Cornell Hospitality Q, 39 (1998), 32-39. doi: 10.1177/001088049803900308.
[6]	A. Lasek, N. Cercone and J. Saunders, Restaurant sales and customer demand forecasting: Literature survey and categorization of methods, Smart City 360, 166 (2016), 479-491. doi: 10.1007/978-3-319-33681-7_40.
[7]	M. S. Morgan and P. K. Chintagunta, Forecasting restaurant sales using self-selectivity models, J. Retail. Consum. Serv, 4 (1997), 117-128. doi: 10.1016/S0969-6989(96)00035-5.
[8]	D. Reynolds, I. Rahman and W. Balinbin, Econometric modeling of the U.S. restaurant industry International, J. Hospitality Manage, 34 (2013), 317-323.
[9]	K. Ryu and A. Sanchez, The evaluation of forecasting methods at an institutional foodservice dining facility, J. Hospitality Financ. Manage, (2013), 27-45. doi: 10.1080/10913211.2003.10653769.
[10]	K. F. Sellers and G. Shmueli, Predicting censored count data with COM-Poisson regression, Working Paper, Indian School of Business, Hyderabad, 2010.
[11]	J. T. Wulu Jr, K. P. Singh, F. Famoye, T. N. Thomas and G. McGwin, Regression analysis of count data, J. Ind. Soc. Ag. Statistics, 55 (2002), 220-230.