Browse > Article
http://dx.doi.org/10.21219/jitam.2017.24.1.111

Comparison of Performance between MLP and RNN Model to Predict Purchase Timing for Repurchase Product  

Song, Hee Seok (Department of Global IT Business in Hannam University)
Publication Information
Journal of Information Technology Applications and Management / v.24, no.1, 2017 , pp. 111-128 More about this Journal
Abstract
Existing studies for recommender have focused on recommending an appropriate item based on the customer preference. However, it has not yet been studied actively to recommend purchase timing for the repurchase product despite of its importance. This study aims to propose MLP and RNN models based on the only simple purchase history data to predict the timing of customer repurchase and compare performances in the perspective of prediction accuracy and quality. As an experiment result, RNN model showed outstanding performance compared to MLP model. The proposed model can be used to develop CRM system which can offer SMS or app based promotion to the customer at the right time. This model also can be used to increase sales for repurchase product business by balancing the level of order as well as inducing repurchase of customer.
Keywords
Purchase Timing; Recommender; Neural Network; Recurrent Neural Network; Franchise Business; Repurchase Product;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Agrawal, R., Ieong, S., and Velu, R., Timing When to Buy, ACM Conference on Information and Knowledge Management (CIKM), 2011.
2 Bastien, F., Lamblin, P., Pascanu, R., Bergstra, J., Goodfellow, I., Bergeron, A., Bouchard, N., Warde-Farley, D., and Bengio, Y., Theano : new features and speed improvements, NIPS 2012 deep learning workshop, 2012.
3 Bayus, B., L., "The Consumer Durable Replacement Buyer", Journal of Marketing, Vol. 55, No. 1, 1991, pp. 42-51.   DOI
4 Zhao, G., Lee, M. L., and Wynne, H., Utilizing Purchase Intervals in Latent Clusters for Product Recommendation, Proceedings of the 8th Workshop on Social Network Mining and Analysis (SNAKDD'14), 2014, pp. 1-9.
5 Rendle, S., Freudenthaler, C., and Schmidt-Thieme, L., Factorizing personalized markov chains for next-basket recommendation, In WWW Conference, 2010, pp. 811-820.
6 Sato, M., Izumo, H., and Sonoda, T., Discount Sensitive Recommender System for Retail Business, Proceedings of the 3rd Workshop on Emotions and Personality in Personalized Systems, 2015, pp. 33-40.
7 Wang, J., Sarwar, B., and Sundaresan, N., Utilizing related products for post-purchase recommendation in e-commerce, Proceedings of the fifth ACM conference on Recommender systems, 2011, pp. 329-332.
8 Chiang, D. A., Lee, S. L., Chen, C. C., and Wang, M. H., "Mining interval sequential patterns", International Journal of Intelligent System, Vol. 20, No. 3, 2005, pp. 359-373.   DOI
9 Bengio, Y., Simard, P., and Frasconi, P., "Learning long-term dependencies with gradient descent is difficult", IEEE Transactions on Neural Networks, Vol. 5, No. 2, 1994, pp. 157-166.   DOI
10 Chen, Y. L. and Huang, T. C. K., "Discovering fuzzy time-interval sequential patterns in sequence databases", IEEE Syst. Trans. Man Cybernet Part B, Vol. 35, No. 5, 2005, pp. 959-972.   DOI
11 Glorot, X. and Bengio, Y., Understanding the difficulty of training deep feedforward neural networks, Proceedings of the International Conference on Artificial Intelligence and Statistics(AISTATS'10), 2010.
12 Gould, B. W. and Dong, D., "The Decision of When to Buy a Frequently Purchased Good : A Multi-Period Probit Model", Journal of Agricultural and Resource Economics, Vol. 25, No. 2, 2000, pp. 636-652.
13 Hinton, G. E., Osindero, S., and Teh, Y., "A fast learning algorithm for deep belief nets", Neural Computation, Vol. 18, 2006, pp. 1527-1554.   DOI
14 Hu, Y. H., Huang, T. C., Yang, H. R., and Chen, Y. L., "On mining multi-time-interval sequential patterns", Data Knowledge Engineering, Vol. 68, No. 10, 2009, pp. 1112-1127.   DOI
15 Mulder, W. D., Bethard, S., and Moens, M.-F., "A survey on the application of recurrent neural networks to statistical language modeling", Computer Speech and Language, Vol. 30, No. 1, 2015, pp. 61-98.   DOI
16 Oh, J., Kim, S., Kim, J., and Yu, H., "When to recommend : A new issue on TV show recommendation", Information Sciences, Vol. 280, No. 1, 2014, pp. 261-274.   DOI