ELARA

A personalized skincare recommendation system

Comment

Inspiration

With the vast variety of skincare products available, it is overwhelming for users to choose products that truly suit their unique skin needs. Inspired by the idea of empowering people to make better skincare choices, I created Elara, a personalized recommendation system that goes beyond generic advice. The main goal was to help users find the perfect match for their skin type and needs, making skincare routines more effective and enjoyable.

What it does

Elara is a skincare recommendation system that allows users to input their skin type and desired product type and then generates tailored product recommendations based on these criteria. Elara not only provides relevant suggestions but also saves previous recommendations, giving users a chance to revisit products that align with their skincare goals.

How we built it

I used Python and Flask for the backend to power the recommendation engine, which leverages TF-IDF and cosine similarity to suggest products based on textual similarities. The user interface was crafted with HTML, CSS, and JavaScript, supported by Bootstrap for responsiveness and user-friendly design. The recommendations are generated based on an dataset of skincare products, which includes essential details like ingredients and skin type compatibility.

Challenges we ran into

One major challenge was fine-tuning the recommendation engine to obtain highly relevant results. I had to experiment with various approaches for data processing and similarity metrics to obtain good recommendation quality and response speed. Additionally, creating an intuitive user interface required careful attention to design, ensuring that users could seamlessly interact with the application on different devices.

Accomplishments that we're proud of

I'm proud to have developed a recommendation system that feels genuinely helpful to users. Creating a functional and easy-to-navigate interface that complements a powerful recommendation algorithm was an accomplishment in itself. I'm also thrilled that Elara can store previous recommendations, allowing users to track and revisit their personalized suggestions. This feature enhances the user experience by making recommendations feel more meaningful and consistent.

What we learned

Building Elara taught a lot about balancing data science and user experience. I learned how essential it is to simplify technical features for ease of use, especially when dealing with personalized recommendations. Also, I gained valuable experience in developing a scalable recommendation system that can adapt to different user needs without sacrificing accuracy.

What's next for Elara - Skincare Recommendation System

I envision expanding Elara to include more skincare product categories and even additional features like personalized routines or ingredient-based filtering for sensitive users. Ultimately, I want Elara to evolve into a go-to digital skincare assistant, helping users make smarter skincare choices and empowering them to feel confident in their own skin.

Share this project:

Updates