rotemknat/goal-contribution-efficiency-top-5-leagues

---
language:
- en
license: cc-by-4.0
pretty_name: "Football Analytics: Efficiency vs. Volume (2019-2020)"
tags:
- sports
- football
- data-science
- xG
- analytics
- tabular
size_categories:
- 1K<n<10K
---

# ⚽ Football Player Performance Analysis (2019-2020)

### 📋 Project Overview
This project explores player performance data across the **Top 5 European Leagues** (England, France, Germany, Italy, and Spain) during the 2019-2020 season. Using a dataset of **2,661 players** and **22 columns**, we analyze the relationship between actual scoring output and expected metrics.

### ❓ Research Question
> **"Do top-tier goal contributors consistently exceed their expected metrics (xG and xA), or is their high output simply a result of high volume?"**

---

### 🎥 Project Demo (Video)

<div align="center">
<video src="https://huggingface.co/datasets/rotemnn97/goal-contribution-efficiency-top-5-leagues/resolve/main/%D7%94%D7%92%D7%A9%D7%94.mp4" width="800" controls></video>
</div>

---

### 📊 Visual Insights
Below are the key analyses performed on the season's data:

#### 1. Expected vs. Actual Performance
This graph displays the gap between actual performance and statistical expectations (xG/xA), allowing for the identification of exceptionally efficient players.

#### 2. League Efficiency Distribution
An analysis of the distribution of efficiency and goal contributions across each of the top 5 leagues.

---

### 🧮 Data & Methodology
The analysis focuses on several key metrics:
* **Total Involvement:** The sum of goals and assists ($Goals + Assists$).
* **Expected Involvement (xI):** The total expectation metric ($xG + xA$).
* **Efficiency Delta:** The difference between actual performance and expected metrics.
* **Filtering:** To ensure statistical significance, we focused on players who played at least **900 minutes**.

#### Data Dictionary (Key Fields)
| Field | Description |
| :--- | :--- |
| `player_name` | Full name of the player |
| `league` | The league (EPL, La Liga, etc.) |
| `minutes_played` | Total minutes on the pitch |
| `goals` / `assists` | Actual statistical output |
| `xG` / `xA` | Expected goals/assists based on shot/pass quality |

### 🛠️ Built With
* **Python** (Pandas, Matplotlib, Seaborn)
* **Jupyter Notebooks**
* **Hugging Face Datasets**

---

### 📜 Attribution & License
Data originally sourced from **In-depth Soccer Statistics (Kaggle)**.
This project was developed as part of an academic assignment in Data Science.