Author(s)

Bidhan Dolai^1*, Indrajit Ghosh²

Affiliation(s)

¹Research Scholar, SGBAU, MH, India.

²Libary Attendant, Baba Saheb Ambedkar Education University, West Bengal, India.

Corresponding Author

Bidhan Dolai

ABSTRACT

Drawing on the existing literature pertaining to the online marketplace, it can be seen that in such a marketplace, consumer ratings of products are the most important predictors of their success and customer satisfaction. This paper, therefore, drew on data sourced from Kaggle and focusing on Amazon books from the year 2009 to 2019, examined the correlations among three main variables, namely Year of release, Price, and the number of Reviews and User Ratings. It was established through multiple regression analysis that Price and Year markedly affect User Ratings while Reviews had a marginally significant effect. An explanation could be that with an increase in price, the users tend to give low ratings which suggests that there is a likelihood of dissatisfaction amongst the consumers, as opposed to older books which generally tend to score lower user ratings because of existing demand for newer works. Considering the R2 value of 0.074, only 7.4% of the variation in User Ratings can be accounted for by the given variables, thus, more predictors will be required in subsequent investigations. Essentially, the present study sheds light on factors affecting user’s satisfaction, in particular, the role of pricing and the timing of releases in satisfying the users.

KEYWORDS

Kaggle data; Rating prediction; Data analytics

CITE THIS PAPER

Bidhan Dolai, Indrajit Ghosh. Leveraging price and time data to enhance user rating predictions of Amazon book: based on kaggle data. World Journal of Economics and Business Research. 2024, 2(2): 12-15. DOI: https://doi.org/10.61784/wjebr3016.

REFERENCES

[1] Hong C, & Zhu K. ENHANCING YELP RATING PREDICTIONS. 2021. https://charleshong3.github.io/projects/cs182_yelp.pdf.

[2] Tayfur G. Real-time flood hydrograph predictions using rating curve and soft computing methods (GA, ANN). Handbook of Hydroinformatics, 2023.

[3] Angelini G, Candila V, Angelis L D. Weighted Elo rating for tennis match predictions. European Journal of Operational Research, 2022, 297(1): 120–132. DOI: https://doi.org/10.1016/j.ejor.2021.04.011.

[4] Kutlimuratov A, Abdusalomov A, Whangbo T K. Evolving hierarchical and tag information via the deeply enhanced weighted non-negative matrix factorization of rating predictions. Symmetry, 2020, 12(11). https://www.mdpi.com/2073-8994/12/11/1930.

[5] Lin Y, Ren P, Chen Z, et al. Meta matrix factorization for federated rating predictions. 2020. DOI: https://doi.org/10.1145/3397271.3401081.

[6] Jiangzhou D, Songli W, Qi W. A linguistically asymmetric similarity decision model integrating item tendency for rating predictions, 2024. DOI: https://doi.org/10.1177/01655515231220172.

[7] Saaidin S, Kassim M. Recommender system: Rating predictions of steam games based on genre and topic modelling. 2020 IEEE International Conference, 2020. https://ieeexplore.ieee.org/abstract/document/9140194/.

[8] Giovanni A, Candila V. Weighted Elo rating for tennis match predictions. European Journal of Operational Research, 2021, 297(1), 120–132. https://iris.uniroma1.it/handle/11573/1556145.

[9] Zuva T, Zuva K. Grouping recommender system users in distinct technology diffusion classifications for rating predictions. Academia, 2020. https://www.academia.edu/download/62182979/AC-6420200224-111807-r5uqw9.pdf.

[10] Ashokan A, Haas C. Fairness metrics and bias mitigation strategies for rating predictions. Information Processing & Management, 2021. https://www.sciencedirect.com/science/article/pii/S0306457321001369.