Supervisor: Dr. Tam, Anthony T.C
Group Member: Choi Tsz Long
Project Introduction
Hong Kong is one of the largest toy importers in the world, From 2019 statistics, the toy import trade value of Hong Kong is over 1.5 million, being the 7th largest in the world, showing the market’s economic influences and Hong Kong people’s high purchasing power to toys (World Integrated Trade Solution, 2019). However, such potential is hindered by inadequate channels to buy or sell toys online in Hong Kong. Most local toy stores, except a few large ones, do not provide e-commerce or online shop services and only have brick-and-mortar stores. As a result, there is insufficient market information available for consumers online, which leads to a information asymmetry and encourages scalping. This ultimately damages the market ecology and makes consumer lose faith in Hong Kong’s local toy market.
Indeed, there are a few popular platforms that people can purchase toys from, such as Taobao, Amazon, and Carousell, but they are either not localised for Hong Kong or not specialised for trading toys, which cannot provide the most optimised functionalities or UI designs a for trading toys. This further limits the potential of Hong Kong’s toy market.
Therefore, the objective of this project is to develop a one-stop platform specialised for e-commerce for buying/selling toys in Hong Kong, which can solve the said problems and unleash the potential of Hong Kong’s local toy market.
Project Progress
Project Report
Project Presentation Slides
Project Poster
Project Video
References
Banerjee, P. (2020). Recommender Systems in Python. Retreived from:
https://www.kaggle.com/code/prashant111/recommender-systems-in-python
Deutschman, Z., (2023). Recommender Systems: Machine Learning Metrics and Business
Metrics. Retrieved from: https://neptune.ai/blog/recommender-systems-metrics
EVIDENTLY AI (2025). 10 metrics to evaluate recommender and ranking systems. Retreived
from: https://www.evidentlyai.com/ranking-metrics/evaluating-recommender-systems
GeeksforGeeks (2024). SVD in Recommendation Systems. Retrieved from:
https://www.geeksforgeeks.org/svd-in-recommendation-systems/
GeeksforGeeks (2025). Understanding TF-IDF (Term Frequency-Inverse Document
Frequency). Retreived from: https://www.geeksforgeeks.org/understanding-tf-idf-term-
frequency-inverse-document-frequency/
HK01 (2022). 高達模型炒風不斷｜MG 大魔$300 炒到$900 轉售 Gundam 模型月入 10
萬原文網址: 高達模型炒風不斷｜MG 大魔$300 炒到$900 轉售 Gundam 模型月入 10 萬
| 香 港 01. Retrieved from:
https://www.hk01.com/%E9%81%8A%E6%88%B2%E5%8B%95%E6%BC%AB/775830/%
E9%AB%98%E9%81%94%E6%A8%A1%E5%9E%8B%E7%82%92%E9%A2%A8%E4%
B8%8D%E6%96%B7-mg%E5%A4%A7%E9%AD%94-300%E7%82%92%E5%88%B0-
900-
%E8%BD%89%E5%94%AEgundam%E6%A8%A1%E5%9E%8B%E6%9C%88%E5%85%
A510%E8%90%AC
HK Ulifestyle (2024). Retrieved from:
https://www.facebook.com/photo.php?fbid=911125491054751&id=100064719244865&set=
a.631855555648414
Hug (2015). Welcome to Surprise’ documentation! Retrieved from:
https://surprise.readthedocs.io/en/stable/
Kumar, S., (2024). A Guide to User Behavior Modeling. Retrieved from:
https://blog.reachsumit.com/posts/2024/01/user-behavior-modeling-recsys/
Milankovich, M. (2015). The Cold Start Problem for Recommender Systems. Medium.
Retrieved from: https://medium.com/@markmilankovich/the-cold-start-problem-for-
recommender-systems-89a76505a7
Scikit-learn (2025). Scikit-learn. Retrieved from: https://scikit-learn.org/stable/index.html
Shaw, A. (2019). Product Recommendation System for e-commerce. Kaggle. Retrieved from:
https://www.kaggle.com/code/shawamar/product-recommendation-system-for-e-commerce
World Integrated Trade Solution (2019). Toys nes imports by country in 2019. Retrieved from:
https://wits.worldbank.org/trade/comtrade/en/country/ALL/year/2019/tradeflow/Imports/part
ner/WLD/product/950390