Hi! I'm Reuben!

Unlock Data-Driven Success: Empower Your Business
with Predictive Analytics and ML-Powered Insights

Full Stack Developer and Certified Professional Data Scientist with a Bachelor's degree in Economics, diverse experience in full-stack software development, and a strong background in data analysis, statistical modeling, and machine learning. Seeking a stable full-time or part-time position where I can demonstrate my skills and gain valuable experience.

Services

Data Preparation
& Management

Ensure Your Data Works for You

  • Strategic data sourcing aligned with business objectives.
  • Streamlined data collection, cleaning, and automated transformations.
  • Development of efficient data workflows for seamless operations.

Exploratory Data
Analysis

Discover Insights Hidden in Your Data

  • Uncover patterns and trends vital to your decision-making.
  • Rigorous data exploration and application of statistical methodologies.
  • Reproducible analysis for transparent and actionable results.

Predictive Analytics
& Machine Learning

Harness the Future with Data-Driven Predictions

  • Extract value through predictive models and cutting-edge ML.
  • Selection of appropriate data science techniques and methodologies, including supervised, unsupervised, and clustering algorithms.
  • Comprehensive model development, evaluation, and seamless integration.

Data Visualization
& Deliverables

Present Insights Through Visual Storytelling

  • Creation of compelling static and interactive data visualizations.
  • Effective communication of information through graphs, plots, and infographics.
  • Delivery of actionable data insights through reports and interactive dashboards.

Portfolio

View Github

innov8finance: interactive market dashboard

A versatile market dashboard. Accessible both online (@innov8finance) and locally, ensuring uninterrupted access to historical tick data for traders to backtest and analyze strategies.

Key features include: Full List of S&P 500 Component Stocks, Sector Filtering, Trending Stocks, Comprehensive Stock Info, Intra-sector Data, etc.

DASH ● PLOTLY ● YFINANCE API ● SQL ● PYTEST ● PYPI

View Github

pixiv bot

An asynchronous bot to upload top-ranked illustrations from Pixiv (a Japanese illustration community service (imageboard) for anime-style art and high-quality illustrations) to the @top_pixiv telegram channel.

ASYNCIO ● AIOGRAM ● AIOHTTP ● APSCHEDULER ● BS4

View Github

ML Kaggle Competition

A predictive model was developed to determine the survival outcomes of Titanic passengers. The project involved EDA, feature engineering, correlation analysis, and model training. A thorough selection process was undertaken using Nested Cross-Validation, with the evaluation of multiple models.

The final model achieved an accuracy score of 0.80382 on the private test dataset, placing it in the top 3% among competition participants.

SKLEARN ● XGBOOST ● OPTUNA ● SEABORN ● PANDAS

View Github

Applied Data Science Capstone Project

The project involved assuming the role of a Data Scientist working for a startup intending to compete with SpaceX, and following the Data Science methodology involving data collection, data cleaning and wrangling, exploratory data analysis, data visualization, feature engineering, model development, model evaluation, and reporting results to stakeholders. View report here.

SKLEARN ● FOLIUM ● SQL ● REQUESTS ● NUMPY

Education

Data Scientist Professional Certificate

View

September 2023

IBM Data Science Professional Certificate (with Honors)

View

June 2023

Bachelor's Degree in Economics at Belarusian State Economic University

  • higher mathematics
  • statistics
  • econometrics and economic-mathematical methods and models
  • computer information technology
  • computer information systems

2018-2022

Data Analysis with Python

View

Scientific Computing with Python

View
See more on LinkedIn...

Experience

Senior Python Software Engineer | CryptoSearchTools

January 2025 - Present

  • Develop and maintain a data aggregation and analysis engine, ensuring high performance and scalability while integrating APIs and SQL databases to streamline workflows.
  • Implement automated data extraction from unstructured text using graph traversal algorithms, NLP, LLMs, and ML methods, improving data accuracy and enabling complex analytics.
  • Build and customize software extensions to meet client requirements, enhancing functionality and satisfaction.

Full Stack Developer | Flame Raiders

November 2023 - December 2024

  • Spearheaded the full-stack development of proprietary community management software for official PUBG: Battlegrounds Discord servers, improving community engagement and administrative efficiency.
  • Engaged millions of users across multiple official gaming communities by developing and providing automated features such as contests, quests, polls, giveaways, and mailings, driving a 24% increase in user participation.
  • Developed a session-based authentication system with Argon2id password hashing and verification, securing dashboard access and user data by enforcing role-based privileges and enhancing overall system security.
  • Ensured minimal downtime and increased performance while reducing server costs by 68% by initiating system design discussions and managing server infrastructure using Docker and GitHub Actions for continuous deployment.

Software Engineer | Independent Contractor

August 2022 - November 2023

  • Built a data pipeline for a media content platform, collecting data from various sources and aggregating it into a centralized database, improving data accessibility and supporting enhanced content discovery.
  • Improved prospect targeting accuracy by filtering out low-value leads, achieving an R-squared value of 0.76 by developing and deploying an XGBoost regression model for a retail agency.
  • Increased homepage engagement for a culinary website by training a Random Forest model using scikit-learn to predict high-traffic content with 82% precision, boosting website traffic and subscriptions.
  • Developed websites, dashboards, automation scripts, and deployed Telegram and Discord bots for local independent businesses and private clients, enhancing their online presence and automating key processes.

Data Analyst | Alfa-Bank

February 2022 - August 2022

  • Automated weekly and monthly department reports, cutting manual reporting time by 4 hours per week and providing insights for senior management decision-making, leveraging Seaborn, Pandas, and Mercury.
  • Performed market analysis of communication peripherals, securing a 47% reduction in expenses while improving call center working conditions and enhancing customer satisfaction.
  • Ensured high automatic speech recognition performance, achieving a 19% higher signal-to-noise ratio (SNR) and reducing word error rates, by analyzing microphone models for a number of use cases in noisy environments.

Technical Skills:

  • Programming Languages: Python, C#, Java, JavaScript (Typescript), HTML (HTMX), CSS (SCSS), SQL, Bash
  • Database Management: PostgreSQL, MySQL, SQLite, MongoDB, Redis
  • Libraries/Frameworks: scikit-learn, xgboost, langchain, optuna, sanic (fastapi/flask), jinja2, react.js, pandas, numpy, scipy
  • Data Visualization: plotly, dash, matplotlib, seaborn, grafana
  • Data Extraction & Web Automation: requests (aiohttp), beautifulsoup (selectolax), playwright
  • Development Tools: Docker, Git, VS Code, Vim, Jupyter Notebook, Conda, PDM

About Me

My name is Reuben, and I provide software development and data science services. I hold a Bachelor's degree in Economics and numerous certifications in the fields of computer and data science, including two Professional Data Science Certifications.

As a Full Stack Data Scientist with diverse experience in software development and a strong background in data analysis, statistical modeling, and machine learning, I specialize in developing end-to-end software solutions and transforming data into valuable insights. My experience with backend, frontend, SQL, Docker, and Linux enables me to handle the full software development lifecycle, from design to deployment and beyond. Additionally, my expertise in data science allows me to present insights effectively through clear visualizations and interactive dashboards. My goal is to develop impactful software solutions that make a difference.

I have an analytical mindset, enjoy problem-solving, and have always been interested in computers and digital technology. My programming journey began during my final year at lyceum, and it became a serious pursuit during my second year at university. It was during this time, while studying Econometrics and encountering regressions for the first time, that I was captivated by the realm of data and predictive analysis. I am passionate about learning and have the skills to adapt quickly to new environments and technologies. My next milestones include mastering deep learning techniques like CNNs, RNNs, GANs, and Transformers, along with industry-standard tools such as MLflow and DVC.

Outside of programming and data science, I enjoy listening to instrumental music, watching anime, reading sci-fi books, and playing with my cat. My main hobby is collecting portable HiFi audio technology.