Skip to content

Data Science · Major Project

Stock Price Forecasting with Prophet & LSTM

Compares a statistical and a deep forecaster on the same stock history

3-4 weeks build

Overview

A forecasting study that pulls daily price history for a handful of NSE-listed stocks, fits Facebook Prophet and a stacked LSTM on identical train windows, and scores both with walk-forward validation. It is framed as a time-series learning exercise, not investment advice, and the report is candid about why short-horizon prices are so hard to forecast.

What makes it stand up

  • 01Prophet and LSTM trained on the same splits for a fair comparison
  • 02Walk-forward validation instead of a single random split
  • 03Naive last-value baseline that both models have to beat
  • 04MAE, RMSE and MAPE per horizon with residual plots
  • 05Explicitly a learning exercise, with a not-investment-advice notice in the app

Module breakdown

  1. 01

    Data pipeline

    Downloads OHLC history, handles holidays and missing sessions.

  2. 02

    Prophet model

    Trend and seasonality components with tuned changepoints.

  3. 03

    LSTM model

    Windowed sequences, scaling and early stopping in Keras.

  4. 04

    Backtesting

    Rolling-origin evaluation against a naive baseline.

  5. 05

    Dashboard

    Streamlit app to pick a ticker, horizon and model.

After this, you will be able to

  • Explain the difference between additive decomposition and recurrent models
  • Defend walk-forward validation over a shuffled train-test split
  • Demo both forecasts side by side and discuss where each one fails

Technology stack

  • Python
  • Pandas
  • Prophet
  • TensorFlow
  • Streamlit

Complete kit

₹7,299₹12,499
-42%
Order this kitAsk a question first

Delivered in under 48 hours

Level
Major Project
Domain
Data Science
Build time
3-4 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
Compare tiers

Keep looking

Students also considered

All projects
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
Mini Project

Data Science

Social Sentiment Dashboard

Track opinion on a topic over time, with aspect breakdown

  • Python
  • Pandas
  • Transformers
  • Plotly
  • +1
₹2,499₹4,399
4.6/238 reviews
Mini Project

Data Science

COVID-19 Case Forecasting with LSTM

Forecasts daily case counts with LSTM against classical baselines

  • Python
  • TensorFlow
  • Pandas
  • statsmodels
  • +1
₹5,499₹9,299