Ensemble Dynamic Machine Learning Algorithm (EDMLA) for E-commerce sentiment product recommendation system with the integration of AACSD-an empirical study-Reference-Cited by-同舟云学术

Ensemble Dynamic Machine Learning Algorithm (EDMLA) for E-commerce sentiment product recommendation system with the integration of AACSD-an empirical study

Published:2023 Issue:1 Volume:1 Page:12
ISSN:2583-9128
Container-title:i-manager's Journal on Artificial Intelligence & Machine Learning
language:en
Short-container-title:JAIM

Author:

Sujay V.¹,M. Babu Reddy¹

Affiliation:

1. Krishna University

Abstract

In this paper, an attempt has been made to investigate the benefits of the Amalgamate Architecture Centric Software Development (AACSD) method through an experimental setup using Machine Learning techniques on an E-Commerce product recommender system. The system recommends products based on authorized user reviews. As part of this research, an Ensemble Dynamic Machine Learning Algorithm (EDMLA) was designed and developed with the integration of AACSD to improve performance quality. Performance was evaluated based on parameters such as sensitivity, specificity, and accuracy.

Publisher

i-manager Publications

Reference12 articles.

1. Alpaydin, E. (2004). Introduction to Machine Learning (Adaptive Computation and Machine Learning Series). The MIT Press Cambridge.

2. Deep Learning: Methods and Applications

3. An approach to improve the accuracy of probabilistic classifiers for decision support systems in sentiment analysis

4. Jotheeswaran, J., & Koteeswaran, S. (2015). Decision tree based feature selection and multilayer perceptron for sentiment analysis. Journal of Engineering and Applied Sciences, 10(14), 5883-5894.

5. Lafferty, J., McCallum, A., & Pereira, F. C. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. ICML '01: Proceedings of the Eighteenth International Conference on Machine Learning, (pp. 282–289).