Mini Project
Data Science
Personal Finance Analytics
Statement parsing, auto-categorisation and spend forecasting
- Python
- Pandas
- Prophet
- Streamlit
- +2
₹2,299₹3,999
4.5/198 reviews
Data Science · Major Project
Fashion Trend Forecasting
Forecasts which styles are rising from search and sales history
2-3 weeks build
Overview
Combines Google Trends CSV exports for style keywords with a public retail sales dataset to track how interest in items such as cargo trousers or co-ord sets rises and fades. Each series is decomposed, clustered by shape into rising, seasonal and fading groups, and forecast with Prophet. A dashboard ranks styles by projected growth for the coming season.
What makes it stand up
- 01Keyword interest series from Google Trends CSV exports
- 02Seasonal decomposition of every style series
- 03Time-series clustering into rising, seasonal and fading groups
- 04Per-style Prophet forecasts with backtesting
- 05Season-ahead ranking of styles by projected growth
Module breakdown
- 01
Data assembly
Merges trend exports and sales records on a weekly grid.
- 02
Decomposition
Separates trend, seasonality and residual per style.
- 03
Clustering
Groups styles by normalised curve shape with k-means.
- 04
Forecasting
Fits and backtests a Prophet model per series.
- 05
Dashboard
Streamlit ranking, style drill-down and forecast bands.
After this, you will be able to
- Explain why search interest can lead sales
- Defend your backtesting window and error metric
- Demo the season-ahead ranking and justify its top pick
Technology stack
- Python
- Pandas
- Prophet
- scikit-learn
- Streamlit
- Level
- Major Project
- Domain
- Data Science
- Build time
- 2-3 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support