Quantitative Rigor. Product Craft.
Core Mission
To build performant systems and predictive analytics architectures that transform raw data streams into high-impact operational tools.
Professional Journey
My entry into technology began in Computer Science & Engineering, where I fell in love with algorithmic structure and data organization. Over time, I discovered that software is only half the puzzle—the real value lies in the data flowing through it.
This realization led me to focus on Data Science and quantitative analytics. Today, I build systems that are both computationally robust and capable of generating actionable intelligence.
Problem Solving
I treat code and modeling with the same logical rigor. When building databases, pipelines, or ML classifiers, I design defensively and verify empirical metrics (precision, recall, latency) at every iteration. I avoid quick hacks in favor of clean, structural code.
Technical Philosophy
Excellent engineering requires empathy. Whether it is a back-end transaction cache or an analytical visualizer, my background in design allows me to translate complex back-end architectures into clean, intuitive interfaces that recruiters and developers enjoy using.
Growth & Motivation
I am driven by structural efficiency—getting a dataset cleanly preprocessed or refactoring a complex codebase into elegant services.
Currently, I am expanding my knowledge in advanced statistical forecasting and real-time streaming architectures to further strengthen my full-stack capabilities.
Capabilities & Systems
Analytical Engine & ML Pipeline
Processing → ModelingOperates on raw datasets drawn from database layers. Scripts clean anomalies, execute feature scaling, and pass optimized data arrays to predictive algorithms for multi-class classification and forecasting.
Data Pipelines & Schemas
Ingestion → IntegrationActs as the structural repository. Implements indexing, schemas, and optimized query routines to deliver datasets cleanly to preprocessing frameworks or transactional microservices.
Business Intelligence & Analytics
Aggregation → VisualizationTranslates SQL metrics and Python model outputs into interactive executive reports. Employs relational modeling and custom DAX calculations to isolate operational risks for decision-makers.
Full-Stack Application Delivery
Interface ← API IntegrationEngineers the client-facing application layers. Uses server-side caching and API gateways to bind databases and machine learning endpoints to clean, responsive interfaces.
Professional Journey
The Problem
High-volume transactional flows presented complex vectors for transaction fraud and financial leakage. Detecting these anomalies required analytical logic, risk assessment, and systematic database queries.
Workflow & Responsibilities
Conducted daily audits of transaction datasets using SQL query logic. Designed and validated structured rule-filters to detect suspicious behavior patterns and anomalies. Investigated high-risk merchant profiles and verified accounts.
Business Value
Mitigated financial liabilities by delivering high-precision risk metrics and predictive reports to operations, leading to data-driven security policies.
Lessons Learned
I learned that data auditing requires absolute precision and logical rigor. Speed is useless without systematic verification, especially in high-risk financial datasets.
The Problem
Raw logs and user engagement data sat in disparate siloed formats, limiting the capacity of analytics to identify retention curves or predict customer attrition triggers.
Workflow & Responsibilities
Built and optimized ETL and feature-extraction pipelines in Python. Conducted Exploratory Data Analysis (EDA) to map active retention metrics. Trained and fine-tuned gradient-boosted classification models (XGBoost) for user profiling.
Business Value
Provided the data infrastructure and preprocessed records that powered downstream stakeholder dashboards, cutting manual data queries for analytics by hours.
Lessons Learned
Building machine learning models is only a fraction of the challenge; feature engineering, data hygiene, and translating quantitative metrics into actionable business context are where true values are made.
Education
Bachelor of Science in Computer Science
2021-2025 | Tagore Engineering College(AU)Coursework highlights: Data Structures and Algorithms, Computer Systems Engineering, Data Science.
Online Coursework
2022-2025 | NxtWave Disruptive TechnolgiesCompleted coursework in advanced topics including Web Application Development, Full Stack Engineering, MERN Stack Technologies (SQLite, Express.js, React.js, Node.js).