HeapCoders — Learn | Build | Grow

ML · B.Tech 3rd / 4th year · mini or major · 6–8 weeks guided

Phishing URL and Fake-News Detection with Ensemble Learning

Two-headed classifier used as one product: URL lexical/host features and news TF-IDF/embeddings, voting ensemble, confusion matrices, and a browser-like check page. Dataset cards included so you do not claim production security.

Student project kit

₹14,999/-₹8,999/-

1–4 students · 6–8 weeks guided. College title can be adapted on the counselling call.

Audience

Who it is for

CSE/IT teams mixing ML with a cybersecurity story.

Demo page: URL + optional article text → label, top features, and a downloadable check report.

Branches

CSEITAI & DSCyber

Team size: 1–4 students

Problem

Existing vs proposed

Users still click lookalike links. Single naive Bayes on headlines is a weak mini project unless you add URL features, evals, and a usable UI.

Feature engineering for URLs, text pipeline for claims, ensemble, threshold for “unsure”, and a report the user can forward.

Build

Modules

Pythonscikit-learnURL feature extractFastAPIReactoptional browser bookmarklet

  1. 1. URL model

    • Length, dots, HTTPS, token tricks
    • Host age if available

  2. 2. Text model

    • TF-IDF / embeddings
    • Headline vs body

  3. 3. Ensemble

    • Vote / stack
    • Unsure band

  4. 4. UX

    • Paste check
    • History for a lab user
    • False-positive note

Demo

What you can show

  • Two feature families
  • Unsure class
  • Lab report PDF

Viva

Panel topics

  • Adversarial URLs
  • Dataset bias
  • Why not 100% blocking

Deliverables

Included with the kit

  • Complete source code (ZIP + GitHub-style repo)
  • Database schema and sample data / dataset notes
  • README.md — how to run, stack, modules, and demo path (Windows + college lab)
  • Viva question bank with short answers
  • Two mentor reviews: architecture, then final demo

Related

You may also need

Heart Risk ML — B.Tech ML project kit at HeapCoders
ML

6–8 weeks guided

Heart Risk ML

Clinical tabular ML with SHAP, thresholds, and a clinician-style UI.

₹14,999/-₹8,999/-

View kit
Dropout Early Warning — B.Tech ML project kit at HeapCoders
ML

6–8 weeks guided

Dropout Early Warning

Flags at-risk students from attendance and marks, with counsellor actions.

₹14,999/-₹8,999/-

View kit
Crop Yield Forecast — B.Tech ML project kit at HeapCoders
ML

6–8 weeks guided

Crop Yield Forecast

District-level yield model with weather features and a scenario slider.

₹14,999/-₹8,999/-

View kit