PopularMajor Project
Machine Learning
AI Resume Screening System
NLP pipeline that ranks candidates against a job description
- Python
- spaCy
- scikit-learn
- FastAPI
- +2
₹4,499₹7,999
4.9/214 reviews
Machine Learning · Mini Project
Order Volume Forecasting
Forecasts daily store orders from calendar, holidays and promotions
1-2 weeks build
Overview
Predicts how many orders a store will receive each day using the public Rossmann Store Sales data from Kaggle. Calendar features, state and school holiday flags, promotions and lagged demand feed a LightGBM regressor, which is compared with a seasonal naive baseline. A Streamlit planner lets a store manager test what a promotion might do to next week's volume.
What makes it stand up
- 01Calendar, holiday, promotion and lag features engineered from scratch
- 02Seasonal naive baseline that the model must beat
- 03Time-based validation across rolling windows
- 04Feature importance showing the effect of promotions
- 05What-if planner for promotions and holidays
Module breakdown
- 01
Data prep
Cleans store histories and fills closed days.
- 02
Features
Day-of-week, holidays, promotions and lagged orders.
- 03
Model
LightGBM regressor with tuned parameters.
- 04
Validation
Rolling-origin backtest with MAE and RMSE.
- 05
Planner
Streamlit what-if tool for the coming week.
After this, you will be able to
- Explain lag features and why they risk leakage
- Defend your validation scheme for time-ordered data
- Demo the effect of a promotion on the forecast
Technology stack
- Python
- Pandas
- scikit-learn
- LightGBM
- Streamlit
- Level
- Mini Project
- Domain
- Machine Learning
- Build time
- 1-2 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