Product Diffusion Research Based on Symbolic Regression
With the popularity of on-line shopping increasing, on-line products diffusion becomes the growth of importance for marketing decision. Bass diffusion theory is a classical method of forecasting products sales. In this paper, we introduce symbolic regression method to describe the trend of on-line products diffusion and verify whether Bass model in on-line condition performs good as before. Almost all products exhibit seasonality in their sales pattern. Considering the particularity of on-line shopping, we define monthly, weekly and daily period as the division of on-line season. The models perform differently when frequency of data varies.
KeywordsOn-line products Diffusion Symbolic regression Seasonality Bass model
This work is supported by the National Natural Science Foundation of China (71671024, 71421001, 71601028), the Fundamental Research Funds for the Central Universities (DUT15RC(3)076), Humanity and Social Science Foundation of Ministry of Education of China (15YJCZH198) and Economic and Social Development Foundation of Liaoning (2016lslktzizzx-01).
- 5.Bass, F.M., Jain, D., Krishnan, T., et al.: Modeling the marketing-mix influence in new product diffusion. In: Mahajan, V., Muller, E., Wind, Y. (eds.) New Product Diffusion Models. Kluwer Academic Publisher (2000)Google Scholar
- 14.Kotanchek, M.E., Vladislavleva, E.Y., Smits, G.F.: Symbolic regression via genetic programming as a discovery engine: insights on outliers and prototypes. In: Riolo, R., O’Reilly, U.-M., McConaghy, T. (eds.) Genetic Programming Theory and Practice VII, pp. 55–72. Springer, US (2010)Google Scholar
- 16.Chandrasekaran, D., Tellis, G.J.: Getting a Grip on the Saddle: Cycles, Chasms, or Cascades? PDMA Research Forum, Atlanta, 21–22 October 2006Google Scholar
- 18.Lu, Q., Ye, Q., Law, R.: Moderating effects of product heterogeneity between on-line word-of-mouth and hotel sales. J. Electron. Commence Res. 15(1), 1–12 (2014)Google Scholar