Baek, Janghyun; Tsai, John; Shamoun, Justin; Marable, Muriel; Cui, Ying; Altintas, Ilkay; McAuley, Julian (2020). Amazon Recommender System. In Data Science & Engineering Master of Advanced Study (DSE MAS) Capstone Projects. UC San Diego Library Digital Collections. https://doi.org/10.6075/J08C9TSC

Recommender systems are algorithms that suggest relevant items to users based on data. They generate large revenue for the modern e-commerce industry. 35% of Amazon web sales were generated through their recommended items [source: McKinsey]. This study aims to construct an apparel recommender system for Amazon users through user-rating history, product images and product title text. Multiple deep learning models were built on both readily-available and engineered datasets resulting in a multi-step recommender system. Tableau and a web app are used to display results, along with evaluation measurements.

• 2020-01 to 2020-06

• 2020

• Baek, JH (Janghyun)
• Cui, Ying
• Marable, Muriel
• Shamoun, Justin
• Tsai, John

• Altintas De Callafon, Ilkay
• McAuley, Julian

Download the input data files listed below by following the instructions found here: https://nijianmo.github.io/amazon/index.html
- Clothing_Shoes_and_Jewelry_5.json.gz (Go to the "'Small' subsets for experimentation" section of the document and click on "5-core" and next to the entry "Clothing, Shoes and Jewelry")
- Clothing_Shoes_and_Jewelry.json.gz
- meta_Clothing_Shoes_and_Jewelry.json.gz

Output data files:
- NLP_output_0603.csv (This file is the output from TF-IDF weighted word2vec model. The csv featured products, recommended products and the euclidean distance between the two vectors.)
- Shoes_for_100_users_per_10_products_prediction.csv
- RESULT_image_recommended_product_50k_for_100JH_ver3_all.csv

• DSE MAS - 2020 Cohort

• Collaborative filtering
• Convolutional Neural Network (CNN)
• Data Science & Engineering Master of Advanced Study (DSE MAS)
• Deep learning
• Graph database
• Machine learning
• Natural Language Programming (NLP)
• Neo4j
• Recommender engine
• Recommender system
• Word2vec

• data
• software
• text

• English

Doi: https://doi.org/10.6075/J08C9TSC

Other resource

• Amazon review dataset. https://nijianmo.github.io/amazon/index.html

Creative Commons Attribution 4.0 International Public License

• Baek, JH (Janghyun); Tsai, John; Shamoun, Justin; Marable, Muriel; Cui, Ying

Under copyright (US)

Use: This work is available from the UC San Diego Library. This digital copy of the work is intended to support research, teaching, and private study.

Constraint(s) on Use: This work is protected by the U.S. Copyright Law (Title 17, U.S.C.). Use of this work beyond that allowed by "fair use" or any license applied to this work requires written permission of the copyright holder(s). Responsibility for obtaining permissions and any use and distribution of this work rests exclusively with the user and not the UC San Diego Library. Inquiries can be made to the UC San Diego Library program having custody of the work.

Research Data Curation Program, UC San Diego, La Jolla, 92093-0175 (https://lib.ucsd.edu/rdcp)

2022-11-28