ARCHIVES
VOL. 9, ISSUE 2 (2023)
Forecast the rating of online products using novel deep learning technique
Authors
Md. Ahsan Habib, Asma Akter
Abstract
The term "forecast" refers to a process that takes historical
data as input for making informed estimates to determine future trends.
Nowadays, marketing on online platforms is growing very fast to cope with the
challenges of the decade. Because of this, online product rating is an
essential parameter to measure the admissibility of products to consumers. From
this, an online consumer decides the quality and nobility of the available
products. It helps the consumer make a decision to buy or not. Being a
successful businessman or stakeholder requires the ability to judge online
product ratings. After analysis, the product rating helps a producer reach a
decision on whether to modify their products or not. In this decade, online
marketing has become more commonplace day by day, where consumers buy their
products and give them a numerical rating, like a star. Producers need to
analyze this rating to drive better revenue in their business. In our paper, we
proposed a hybrid model comprised of long-short term memory (LSTM) and a
convolutional neural network (CNN) that achieves 95% accuracy in online product
review analysis. We applied the model mentioned above to the dataset named
"GrammarandProductReviews." provided by Datafiniti. We have also
applied some supervised machine learning algorithms such as Random Forest,
Support Vector Machine (SVM), Logistic Regression, and XGBoost Algorithm with
TF-IDF vectorize to analyze the customer product text review. Finally, we
understand the findings obtained from the model presented by the various
researchers. From all the studies, we observed that the combination of long-short
term memory (LSTM) and a convolutional neural network (CNN) shows better
performance (95% accuracy) than any other model.
Download
Pages:28-37
How to cite this article:
Md. Ahsan Habib, Asma Akter "Forecast the rating of online products using novel deep learning technique". International Journal of Research in Advanced Engineering and Technology, Vol 9, Issue 2, 2023, Pages 28-37
Download Author Certificate
Please enter the email address corresponding to this article submission to download your certificate.