Trendora

Our Thought Process
Initial Design Idea
Imports from CJDropshipping

Inspiration

We noticed how hard it was to keep up with fast-moving product trends, especially in the dropshipping world. People spend hours scrolling TikTok or scanning AliExpress for what’s hot and still miss the next big thing. We wanted to create a tool that simplifies trend discovery and gives anyone a competitive edge.

What it does

Our system lets users type in a query like “trending coffee products,” and it does the heavy lifting from there. It breaks down the input, finds real-time trending keywords, searches multiple product platforms (AliExpress, TikTok Shop, etc.), analyzes the results, and displays the top-performing items based on past and predicted trends, all in one place.

How we built it

We started by connecting NLP to parse user prompts into actionable keywords. These keywords are fed into Google Trends, Exploding Topics, and TikTok APIs to extract trend data. From that, we generate a top keyword (e.g., “coffee cupholder”) and use it to search APIs like AliExpress and CJ Dropshipping. Our custom algorithm then scores each product based on sales, reviews, and trend history. The top items are displayed with images, metrics, and growth predictions on a sleek frontend dashboard.

Challenges we ran into

One of the biggest challenges was working with external APIs many of them were behind paywalls or had rate limits, and integrating them involved a lot of debugging and testing. Since we split the project between six people, we had to figure out how to divide responsibilities efficiently and sync our work without conflicts. Another technical challenge was normalizing inconsistent data formats from different APIs and building a trend-scoring system that was accurate and unbiased.

Accomplishments that we're proud of

We’re really proud that we managed to build something genuinely useful for dropshippers having had experience in the space ourselves, we know how hard it is to find products that actually sell. This tool could be a game-changer for people just starting out or scaling up. We’re also proud of how well we worked together as a team despite the tight time frame and multiple moving parts.

What we learned

We learned how to work effectively in a large team, delegate tasks, and stay coordinated. We also learned how to manage our time efficiently and deliver a functional product within just one day.

What's next for To be decided

We want to train our trend prediction model to improve its accuracy and streamline the entire process. We also see potential for expanding this system beyond dropshipping possibly using the same approach to identify trends in areas like academic research, news, or market intelligence.