Research on Escaping the Big-Data Traps in O2O Service Recommendation Strategy

Internet business can be divided into two categories: pure online business and Online to Offline (O2O) business. Currently, the recommendation technology for online business is maturing, such as news, movies, products, and so forth. However, traditional recommendation technology can easily cause the overcrowding at some O2O services because of the big data traps. In the end, the users' experience with the O2O service recommendation is useless or very poor because they have to wait for a long time and can't enjoy the service immediately. Hence, how to improve the performance of O2O service recommendation has become a vital problem. To solve the problem, this paper proposes a research framework based on the continuous feedback learning mechanism between cyber layer and social layer. Then, the continuous feedback ideas are implemented in the design of the O2O service recommendation strategy step by step. Furthermore, the computational experiment system is constructed to perform performance analysis of these service strategies. The results show that our research framework is conductive to help O2O service recommendation to escape the big-data traps and to improve user experience.

Automated summary

The paper discusses the categorization of internet business into pure online and O2O business, highlighting the need to improve O2O service recommendation through continuous feedback learning between cyber and social layers. The proposed research framework enhances user experience and helps O2O services escape big-data traps, as demonstrated by computational experiments.