https://github.com/guiarpi/lgbtqi-hate-crime-analysis
Machine Learning analysis of LGBTQI+ hate crimes in the U.S
https://github.com/guiarpi/lgbtqi-hate-crime-analysis
decision-trees eda etl k-means-clustering knn-classification linear-regression machine-learning multiple-linear-regression r random-forest rstudio sql tableau
Last synced: 10 days ago
JSON representation
Machine Learning analysis of LGBTQI+ hate crimes in the U.S
- Host: GitHub
- URL: https://github.com/guiarpi/lgbtqi-hate-crime-analysis
- Owner: guiarpi
- Created: 2025-02-25T20:31:23.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-25T20:43:48.000Z (over 1 year ago)
- Last Synced: 2025-02-25T21:33:32.858Z (over 1 year ago)
- Topics: decision-trees, eda, etl, k-means-clustering, knn-classification, linear-regression, machine-learning, multiple-linear-regression, r, random-forest, rstudio, sql, tableau
- Homepage:
- Size: 1.95 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Predicting-LGBTQI-Hate-Crimes-in-the-U.S.-Using-Machine-Learning
## Project Overview:
~Brief description of the project, its goals, and key findings~
In this project, I examined hate crimes against LGBTQI+ individuals in the U.S. from 1991 to 2019, focusing on factors like income inequality, victim counts, LGBTQI+ population size, and anti-LGBTQI+ laws. **Machine learning algorithms** were used to predict and classify these crimes, with an emphasis on evaluating their accuracy. I used different data tools during the elaboration of this study, including **SQL** (for ETL), **R** (EDA and ML) and **Tableau** (Visualizations and Interactive Dashboard).
**Key Strengths**
- **Relevance of Topic:** The project addresses a socially significant issue.
- **Use of ML Algorithms:** I have applied a variety of ML techniques (Decision Tree, Random Forest, K-Means, K-NN) to analyze the dataset.
- **Data Enrichment:** I have added external data (e.g., LGBTQI+ population, Gini Index, hate crime laws) to enhance the analysis.
- **Visualizations:** The use of Tableau and Excel for visualizations adds a layer of clarity to the findings.
- **CRISP-DM Methodology:** The structured approach to data mining is a strong point.
## Dataset:
Information about the dataset (source, variables, etc.).
## Methodology:
Summary of the techniques used (e.g., CRISP-DM, ML algorithms).
## Results:
Key insights and visualizations.
## How to Run the Code:
Step-by-step instructions for reproducing the analysis.
## Dependencies:
List of libraries and tools used (e.g., RStudio, Tableau).
## Future Work:
- Integrating social media data for real-time hate crime prediction.
- Exploring other ML techniques (e.g., neural networks, ensemble methods).
- Expanding the analysis to other countries or regions.