摘要
In this paper, we propose a method that combines models such as GPR with PSO optimization to predict the time series data. We use LSTM and TOPSIS with entropy weight method modification to process various types of data from various aspects, taking into account both tabular and textual data, and to mine valuable contents from them. Based on shopping data, we analyze the historical situation and predict the future sales of products. So that we can recommend the most suitable products for customers. At the same time, for merchants, this paper provides directions for product optimization and improvement of advertising and marketing strategies.
延伸閱讀
- 何維信、黎驥文（1996）。A Study on Data Processing for Land Use Research。地籍測量：中華民國地籍測量學會會刊，15(2)，1-12。https://doi.org/10.29609/YYWYLL.199606.0001
- 徐靈迪（2022）。Probabilistic Goods Sales Strategy and Profit Analysis of Shopping Platform〔碩士論文，國立政治大學〕。華藝線上圖書館。https://doi.org/10.6814/NCCU202200391
- 張藝馨（2015）。Automatic Data Classification and Concept Analysis Based on MapReduce〔碩士論文，中原大學〕。華藝線上圖書館。https://doi.org/10.6840/CYCU.2015.00070
- Hsia, K. H., Chen, M. Y., & Chang, M. C. (2004). Comments on Data Pre-processing for Grey Relational Analysis. Journal of Grey System, 7(1), 15-20. https://doi.org/10.30016/JGS.200406.0003
- 梁思婕（2017）。Application of Logistic Regression on MMN Data〔碩士論文，國立交通大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0030-0705201811553739