Anomaly Detection in Public Company Financial Statements Using Density-Based Clustering

Applied Data Science Master's Program Capstone Project
Shiley Marcos School of Engineering / University of San Diego

Authors

• Andrew Abeles
• Emina Belekanich

Objectives

1. Cluster U.S. public companies based on their most commonly disclosed financial metrics.
2. Identify anomalous U.S. public companies based on their most commonly disclosed financial metrics.

Deliverables

1. White Paper
2. Web Application

Project Organization

---

├── README.md          <- The top-level README.
|
├── requirements.txt   <- Python dependencies. 
|
├── data
│   ├── interim        <- Intermediate data that has been transformed.
│   ├── processed      <- The final, canonical data sets for modeling.
│   └── raw            <- The original, immutable data dump.
|
├── figures            <- Data visualizations saved as image files. 
│
├── notebooks          <- Jupyter notebooks. Naming convention is a number (for ordering)
│                         and a short `-` delimited description, e.g.
│                         `1.0-get-raw-data.ipynb`.
|
├── src
│   ├── data.py        <- Data processing module.
│   └── visualize.py   <- Data visualization module.
│  
|
├── main.ipynb         <- Project white paper.   
|
├── app.py             <- Streamlit app.

---