Multi-Purpose Hybrid Recommendation System on Artificial Intelligence to Improve Telemarketing Performance

다국어 초록 (Multilingual Abstract)

The purpose of this study is to incorporate telemarketing processes to improve telemarketing performance. For this application, we have attempted to mix the model of machine learning to extract potential customers with personalisation techniques to derive recommended products from actual contact. Most of traditional recommendation systems were mainly in ways such as collaborative filtering, which predicts items with a high likelihood of future purchase, based on existing purchase transactions or preferences for products. But, under these systems, new users or items added to the system do not have sufficient information, and generally cause problems such as a cold start that can not obtain satisfactory recommendation items. Also, indiscriminate telemarketing attempts can backfire as they increase the dissatisfaction and fatigue of customers who do not want to be contacted. To this purpose, this study presented a multi-purpose hybrid recommendation algorithm to achieve two goals: to select customers with high possibility of contact, and to recommend products to selected customers. In addition, we used subscription data from telemarketing agency that handles insurance products to derive realistic applicability of the proposed recommendation system. Our proposed recommendation system would certainly solve the cold start and scarcity problem of existing recommendation algorithm by using contents information such as customer master information and telemarketing history. Also. the model could show excellent performance not only in terms of overall performance but also in terms of the recommendation success rate of the unpopular product.

참고문헌 (Reference)

1 Shaw, G., "Using association rules to solve the cold-start problem in recommender systems" 6118 : 340-347, 2010

2 Khribi, M. K., "Toward a hybrid recommender system for e-learning personalization based on web usage mining techniques and information retrieval" 6136-6145, 2007

3 Sarwar, B., "Sparsity, scalability, and distribution in recommender systems" University of Minnesota 2001

4 Mossong, J., "Social contacts and mixing patterns relevant to the spread of infectious diseases" 5 (5): 381-391, 2008

5 Langseth, H., "Scalable learning of probabilistic latent models for collaborative filtering" 74 : 1-11, 2015

6 Bobadilla, J., "Recommender systems survey" 46 : 109-132, 2013

7 Hu, R., "Recommender Systems and the Social Web" 17-24, 2010

8 Lacerda, A., "Multi-objective ranked bandits for recommender systems" 246 : 12-24, 2017

9 Mobasher, B., "Model-based collaborative filtering as a defense against profile injection attacks" 1388-1393, 2006

10 Chen, Y. L., "Market basket analysis in a multiple store environment" 40 (40): 339-354, 2005

11 Sarwar, B., "Item-based collaborative filtering recommendation algorithms" 285-295, 2001

12 Wang, X., "Improving content-based and hybrid music recommendation using deep learning" 627-636, 2014

13 Burke, R., "Hybrid web recommender systems"

14 Burke, R., "Hybrid recommender systems : Survey and experiments" 12 (12): 331-370, 2002

15 Brynjolfsson, E., "Goodbye pareto principle, hello long tail : The effect of search costs on the concentration of product sales" 57 (57): 1373-1386, 2011

16 Ghazarian, S., "Enhancing memory-based collaborative filtering for group recommender systems" 42 (42): 3801-3812, 2015

17 Breese, J. S., "Empirical analysis of predictive algorithms for collaborative filtering" 43-52, 1998

18 Kim, D., "Convolutional matrix factorization for document context-aware recommendation" 233-240, 2016

19 Arsan, T., "Comparison of collaborative filtering algorithms with various similarity measures for movie recommendation" 6 (6): 1-20, 2016

20 Ekstrand, M. D., "Collaborative filtering recommender systems" 4 (4): 81-173, 2010

21 Min, F, "Cold-start recommendation through granular association rules"

22 Ordonez, C., "Association rule discovery with the train and test approach for heart disease prediction" 10 (10): 334-343, 2006

23 Linden, G., "Amazon.com recommendations item-to-item collaborative filtering" 7 (7): 76-80, 2003

24 Reshma, R., "Alleviating data sparsity and cold start in recommender systems using social behaviour" 1-8, 2016

25 Wang, H. C., "Adapting topic map and social influence to the personalized hybrid recommender system" 1-17, 2018

26 Paranjape-Voditel, P., "A stock market portfolio recommender system based on association rule mining" 13 (13): 1055-1063, 2013

27 Wang, Y. F., "A personalized recommender system for the cosmetic business" 26 (26): 427-434, 2004

28 Yang, W. S., "A location-aware recommender system for mobile shopping environments" 34 (34): 437-445, 2008

29 Paradarami, T. K., "A hybrid recommender system using artificial neural networks" 83 : 300-313, 2017

30 Kardan, A. A., "A hybrid recommender system for e-learning environments based on concept maps and collaborative tagging" 300-307, 2009

31 Chen, W., "A hybrid recommendation algorithm adapted in e-learning environments" 17 (17): 271-284, 2014

32 Hu, B., "A hybrid music recommendation system by M-LSA" 1 : 129-132, 2009

33 Christakou, C., "A hybrid movie recommender system based on neural networks" 16 (16): 771-792, 2007

34 Moro, S., "A data-driven approach to predict the success of bank telemarketing" 62 : 22-31, 2014

35 Acilar, A. M., "A collaborative filtering method based on artificial immune network" 36 (36): 8324-8332, 2009