Startups Success Prediction Project

The primary goal of this project is to predict the success of startups transitioning from the early stages of ideation and inception to the scale-up stage by analyzing their Twitter activity.

Project Structure

The repository is organized as follows:

• Project Startups 2.ipynb: The Jupyter Notebook containing the code, analysis, and results for the entire project.
• Startups Project Data Mining.pdf: The comprehensive report generated from the analysis in pdf format
• startup_traction (2).csv: The dataset which contains startup traction data used for this analysis.
• README.md: This file.

DataSources

• Startup Traction data provided in CSV format:

  • startup_traction (2).csv

Analysis and Results

The comprehensive report generated from the analysis

Startups Project Data Mining.pdf

Project Startups 2.ipynb

This project focuses on several key areas of analysis which include:

Data Quality: Identifying and correcting manual errors found in the dataset.

• Exploratory Data Analysis: Evaluation of data distributions, relationships, and their key statistics.
• Predictive Modeling: Developing of models in order to predict future performance and key metrics.
• Visualization: Creation of charts and graphs to illustrate discoveries and trends.

Installation

Requirements

• Python (version 3.6 or higher)
• Jupyter Notebook or JupyterLab
• The following Python packages:
  • pandas
  • numpy
  • matplotlib
  • seaborn
  • scikit-learn

# Setup

Clone the repository:

  git clone https://github.com/Hugongra/startups-x-model.git

cd startups-x-model

Install the required Python packages:

pip install pandas numpy matplotlib seaborn scikit-learn

Usage

To run the analysis, open the Jupyter Notebook file Project Startups 2.ipynb in Jupyter Notebook or JupyterLab and execute the cells.