Inspiration
We drew inspiration from the need to enhance the shopping experience on TikTok Shop by providing users with personalized product recommendations that cater to their unique preferences and circumstances.
What it does
Our E-commerce recommendation system, built using Django, scikit-learn, and Bootstrap, offers hyperpersonalized product suggestions to users based on their input, including product titles, price preferences, and other relevant factors.
How we built it
We employed Django for the web framework, scikit-learn for machine learning tasks, and Bootstrap for a responsive user interface. We also utilized Joblib for saving trained models, Python as the core programming language, and libraries like Numpy, Pandas, and Cosine Similarity from scikit-learn.
Challenges we ran into
We encountered challenges in integrating the open-source library into our project due to version compatibility issues between our system and the library's dependencies.
Accomplishments that we're proud of
We successfully built a functional prototype that provides accurate and personalized product recommendations. We also developed a responsive user interface and integrated machine learning models to enhance the shopping experience on TikTok Shop.
What we learned
We gained valuable experience in developing an E-commerce recommendation system, leveraging machine learning algorithms, and creating a user-friendly interface.
What's next for E-Commerce recommender system
Our next steps include refining the model by incorporating additional user data, expanding the product dataset, and integrating the system with the existing TikTok Shop app to provide a seamless user experience. We also plan to explore using other machine learning algorithms to further enhance the recommendation system.
Log in or sign up for Devpost to join the conversation.