Tyler Anatole

📂 Tyler Anatole — Data Engineering, Analytics & Applied ML Portfolio

Welcome to my technical project portfolio. I’m a Master’s student in Data Science & Engineering (graduating December 2025) building end-to-end data projects, including ELT pipelines with SQL, Python, dbt, and Docker, dimensional data models, and applied NLP systems used for downstream analytics and machine learning. I’m preparing for roles in Data Engineering and Analytics Engineering.

---

🚀 Featured Projects

• Anime Pipeline v2 - Dockerized ELT pipeline using dbt and Postgres for analytics-ready data. (2026)
• Content-Based Matchmaking — NLP with BERT for semantic essay matching + location filters. (2025)
• ETL Search Pipeline — Multi-engine ingestion, OCR, MySQL, dashboard keyword insights. (2025)

---

📌 Current Projects

| Year | Project | Description | Tech Stack | |——|———|————-|————| | 2026 | Anime Pipeline v2 | A Dockerized ELT pipeline that ingests MyAnimeList data via the Jikan API, loads it into Postgres, and models analytics-ready tables using dbt. | | 2025 | Content-Based Matchmaking | Rank profiles by semantic similarity using BERT embeddings + location filtering. | | | 2025 | ETL Search Pipeline | Ingest multi-engine search results, OCR text, store in MySQL, and visualize keyword patterns via dashboard. | |

---

📦 Archived Projects (older coursework, kept for reference)

| Year | Project | Description | Tech Stack | |------|---------|-------------|------------| | 2021 | [Analyzing Borrower Risk](archive/Analyzing%20Borrowers'%20Risk) | Analyzed if marital status and children affect loan default risk. | [](https://pandas.pydata.org/) | | 2021 | [Crankshaft List Analyst](archive/Crankshaft%20List%20Analyst) | Identified factors influencing used car prices. | [](https://pandas.pydata.org/) [](https://numpy.org/) [](https://matplotlib.org/) | | 2021 | [Ice Videogame Analyst](archive/Ice%20Videogame%20Analyst) | Found patterns predicting game success for ad targeting. | [](https://pandas.pydata.org/) [](https://matplotlib.org/) [](https://numpy.org/) [](https://scipy.org/) | | 2021 | [Telecom Plans ML Model](archive/Megaline%20Analyst%20Machine%20Learning%20Project) | Recommended plan upgrades based on usage data. | [](https://pandas.pydata.org/) [](https://matplotlib.org/) [](https://numpy.org/) [](https://scikit-learn.org/stable/) | | 2021 | [Beta Bank Customers](archive/Beta%20Bank%20Customers) | Churn prediction model with focus on F1 score. | [](https://pandas.pydata.org/) [](https://numpy.org/) [](https://scikit-learn.org/stable/) | | 2021 | [Oil Well Model](archive/Oil%20Well%20Model) | Chose most profitable oil region + bootstrap risk analysis. | [](https://pandas.pydata.org/) [](https://numpy.org/) [](https://scipy.org/) [](https://scikit-learn.org/stable/) [](https://matplotlib.org/) | | 2021 | [IMDB Sentiment Analysis](archive/IMDB%20Sentiment%20Analysis) | Detected negative movie reviews from IMDB. | [](https://www.tensorflow.org/) [](https://scikit-learn.org/stable/) [](https://matplotlib.org/) [](https://seaborn.pydata.org/) [](https://lightgbm.readthedocs.io/) [](https://www.nltk.org/) [](https://spacy.io/) | | 2021 | [Time Series Cab Fare Prediction](archive/Timeseries%20Cab%20Fare%20Prediction) | Predicted hourly taxi demand for driver optimization. | [](https://www.python.org/) [](https://scikit-learn.org/stable/) | | 2021 | [Customer Age Detection](archive/Customer%20Age%20Detection%20Project) | CNN to verify age for alcohol law compliance. | [](https://www.python.org/) [](https://keras.io/) [](https://opencv.org/) |

---

📫 Connect

• LinkedIn: linkedin.com/in/tylerana
• Portfolio Site: tylerana.github.io