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
Language Detection
Identifies the language of a sentence from character n-grams
1-2 weeks build
Overview
Detects which language a piece of text is written in, including several Indian languages. Character n-grams capture spelling patterns that stay informative even for short inputs, and multinomial naive Bayes is compared with logistic regression on the public WiLI-2018 dataset. The report looks closely at confusable pairs such as Hindi and Marathi.
What makes it stand up
- 01Character one-to-three-gram features that work on short text
- 02Naive Bayes and logistic regression compared
- 03Covers several Indian languages alongside European ones
- 04Confusion matrix focused on closely related language pairs
- 05Web app that returns the top three languages with probabilities
Module breakdown
- 01
Dataset
WiLI-2018 subset selection and balancing.
- 02
Features
Character n-gram vectoriser with vocabulary pruning.
- 03
Models
Multinomial naive Bayes and logistic regression.
- 04
Evaluation
Accuracy by input length and a per-language F1 table.
- 05
App
Flask page with instant detection as you type.
After this, you will be able to
- Explain why character n-grams beat words here
- Discuss why short inputs are hardest to classify
- Demo detection on sentences in several languages
Technology stack
- Python
- scikit-learn
- Pandas
- Flask
- 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