Price Suggestion and Recommendation of Resale Products on E-commerce Websites

Pereira, Sanchit (2019) Price Suggestion and Recommendation of Resale Products on E-commerce Websites. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (1MB) | Preview

Abstract

E-commerce websites implements recommendation systems for recommending products to the customer and improve their sales. This can be effectively implemented if the website has new brand products, since new brand products have standardized pricing all over the e-commerce platform. But, there are also some e-commerce website which only sell resale products, the products sold on these websites are coming from sellers who have already used that product. So the pricing on these products are not standardized as prices of these products is decided by the seller of those resale products. Since only resale products are sold on these websites, such websites do not have all the products and therefore there is no recommendation system on these websites. The aim of this paper is to predict the prices of the product by considering the characteristics of the product and make the price standardized for all the products. After standardizing all the prices on the e-commerce website, a market basket based recommendation system is built for such e-commerce website. The algorithms used for predicting the prices are Light Gradient Boosting Machine (LGBM), Ridge Regression and Convolutional Neural Network (CNN). CNN outperformed LGBM and ridge regression for predicting the price, the root mean squared logarithmic error value (rmsle) of CNN was 0.44, while LGBM was at 0.53 and ridge regression was at 0.47. Apriori algorithm is used for recommendation system as association rules are implemented for market basket analysis. For generating the association rules the support value used is 0.001, while the value of confidence is 0.90.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software H Social Sciences > HF Commerce > Electronic Commerce
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Caoimhe Ní Mhaicín
Date Deposited:	14 Oct 2019 10:40
Last Modified:	14 Oct 2019 10:40
URI:	https://norma.ncirl.ie/id/eprint/3865

Actions (login required)

View Item