Investment-Management-Analysis

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

Investment-Management-Analysis

★ 9 Open GitHub ↗

No description available.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Investment Management Analysis

## Overview

This project analyzes global startup investment data to help **Spark Funds** identify the best sectors, countries, and investment type for deploying capital. The analysis follows a data-driven approach using real-world funding records.

## Business Constraints

- Investment amount: **$5M – $15M per round**
- Countries: **English-speaking countries only**
- Strategy: invest where most other investors are investing

## Datasets

| File | Description |
|------|-------------|
| `companies.txt` | 66,368 companies with name, permalink, category, country, and status |
| `rounds2.csv` | 114,949 funding rounds with round type, amount (USD), and company reference |
| `mapping.csv` | Maps granular category names to 8 broad sector buckets |

## Methodology

1. **Data Cleaning** — Handle encoding issues, drop irrelevant columns, remove null `raised_amount_usd` rows
2. **Merge** — Join `companies` and `rounds2` on company permalink into a unified `master_frame`
3. **Investment Type Analysis** — Compare mean/median funding across round types
4. **Country Analysis** — Identify top 9 countries by total venture funding; select top 3 English-speaking
5. **Sector Mapping** — Map primary categories to 8 main sectors using `mapping.csv` via `pd.melt`
6. **Sector Analysis** — Filter by country + venture type + $5–15M range; rank sectors by investment count

## Key Findings

### Investment Type
**Venture** is the recommended investment type — it is the most common funding type and its average deal size falls within the $5–15M target range.

### Top 3 Countries (Venture Funding)
1. **USA** — Highest investment volume and total amount
2. **GBR** — Second largest English-speaking market
3. **IND** — Third, with strong activity in digital sectors

### Top 3 Sectors per Country

| Rank | USA | GBR | India |
|------|-----|-----|-------|
| 1st | Others | Others | Others |
| 2nd | Social, Finance, Analytics, Advertising | Social, Finance, Analytics, Advertising | Social, Finance, Analytics, Advertising |
| 3rd | Cleantech / Semiconductors | Cleantech / Semiconductors | News, Search and Messaging |

> **Others** and **Social, Finance, Analytics, Advertising** are consistently top sectors across all three countries.

## Output Files

| File | Description |
|------|-------------|
| `master_frame.csv` | Cleaned and merged dataset with sector assignments |
| `D1.csv` | USA — venture investments in $5–15M range |
| `D2.csv` | GBR — venture investments in $5–15M range |
| `D3.csv` | India — venture investments in $5–15M range |

## Requirements

```
pandas
numpy
matplotlib
seaborn
```

## How to Run

Open `Project-Investment.ipynb` in Jupyter Notebook and run all cells sequentially. Ensure all data files (`companies.txt`, `rounds2.csv`, `mapping.csv`) are in the same directory.

Investment-Management-Analysis

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README