Hi, I'm Siddarth
Quantitative Researcher & Data Scientist specializing in algorithmic trading strategies, financial modeling, and AI-driven market analysis to unlock alpha in modern financial markets.
My Projects
A showcase of my recent work and contributions
Customer Analytics Dashboard
Interactive dashboard for customer behavior analysis using Python, Pandas, and Plotly.
Predictive Analytics Model
Machine learning model for sales forecasting with 95% accuracy using scikit-learn.
Portfolio Tracker App
Full-stack web application for tracking investment portfolios with real-time data.
About Me
Get to know me better
I'm a passionate Data Scientist with a strong background in machine learning, statistical analysis, and full-stack development. My journey in technology began with a curiosity about how data can tell stories and drive meaningful decisions.
With expertise in Python, R, and modern web technologies, I bridge the gap between data science and practical applications. I love creating end-to-end solutions that not only analyze data but also present it in user-friendly interfaces.
I'm particularly interested in quantitative finance and the application of data science techniques to financial markets. Additionally, I'm passionate about generative AI and large language models (LLMs), exploring how these cutting-edge technologies can revolutionize financial analysis and decision-making. While I'm building experience in these domains, I'm eager to explore algorithmic trading, risk modeling, AI-powered financial analysis, and automated trading systems.
When I'm not coding or diving deep into datasets, you'll find me exploring new technologies, studying financial markets, contributing to open-source projects, or sharing knowledge with the developer community.
Technical Skills
Data Science
- Python (Pandas, NumPy, Scikit-learn)
- Machine Learning & Deep Learning
- Statistical Analysis & Time Series
- Data Visualization (Matplotlib, Plotly)
Development
- JavaScript (React, Node.js)
- HTML5 & CSS3
- Database Design (SQL, MongoDB)
- Version Control (Git)
Quantitative Finance (Learning)
- Financial Data Analysis
- Risk Modeling & Portfolio Theory
- Algorithmic Trading Concepts
- Financial Libraries (QuantLib, yfinance)
AI & ML Technologies
- Large Language Models (LLMs)
- Generative AI & Transformers
- Natural Language Processing
- AI Model Fine-tuning
Tools & Platforms
- Jupyter Notebooks & Google Colab
- Docker & Cloud Platforms (AWS, Azure)
- Financial APIs (Alpha Vantage, Yahoo)
- OpenAI API & Hugging Face
Professional Experience
My journey in data science and technology
Data Engineer/Scientist
April 2025 - PresentHitachi Global Air Power
- Applied Recursive Feature Elimination (RFE) with Random Forest and SVM on sales data, reducing 500+ features to 80 key predictors, resulting in 25% reduction in processing time while maintaining 99% prediction accuracy
- Leveraged PySpark to extract and process 10,000+ financial PDFs (200GB) and built OCR model (CNN-LSTM) on Azure Cloud using Keras and TensorFlow, achieving 98.5% accuracy with CTC loss metrics
- Deployed and tested multiple Deep Learning models (Seq2Seq, BERT, DistilBERT) on preprocessed financial data, choosing DistilBERT for its 95.2% accuracy and 50% faster recommendations for sales forecasting
Data Analyst
February 2024 - March 2025Hitachi Global Air Power
- Utilized Python, PySpark, SQL, and Power BI to preprocess and visualize 20GB of financial transaction data, highlighting anomaly patterns and uncovering significant correlations (0.85) between payment behaviors
- Created NLP pipelines using Spacy, Gensim, and NLTK for customer feedback preprocessing, creating streamlined data processing system and cut down processing time by 30% through advanced AI techniques
- Conducted feature engineering on customer behavior data, evaluating individual feature contribution to risk categories leveraging methods such as one-vs-all (Random Forest) and SHAP values
Data Engineer
July 2022 - December 2022Pontoon Solutions
- Designed and developed priority-based fair-share scheduling algorithms for distributed workforce management systems, optimizing resource allocation and improving system throughput by 35% across multiple client environments
- Built scalable ETL workflows using Apache Airflow and Kafka, processing 500GB+ weekly workforce and payroll data with 99.9% uptime, supporting compliance and reporting across 15+ client data sources
- Collaborated with business intelligence team to apply data engineering techniques enabling discovery of 12 new workforce optimization patterns, unlocking new avenues for talent acquisition and placement strategies
Education & Key Projects
2021 - 2023Northeastern University
- Developed scalable quantitative research application using Streamlit, supporting simultaneous analysis of 5+ financial datasets and chunking market data into optimized segments using LangChain and Large Language Models
- Engineered logistic regression and decision tree models for credit risk assessment, achieving 85% accuracy on dataset of 500,000 borrowers, validated through z-tests and chi-square tests at 95% confidence level
- Identified top 8 market risk factors explaining 75% variance via ANOVA analysis, leading to 20% reduction in portfolio risk through targeted quantitative strategies and optimized trading policies
Technical Proficiency
Get In Touch
Let's discuss opportunities and collaborations
Let's Connect
I'm always open to discussing new opportunities, interesting projects, or just having a chat about technology and data science.