DECODING
DATA
DYNAMICS.
Hi, I'm Bhaskar Jha. Bridging the gap between rigorous mathematical theory and modern data engineering. Building intelligent tools with Python, SQL, and Deep Learning. Open source contributor at Open Food Facts.
The
Journey
Google Summer of Code
Contributor for Open Food Facts. Navigating large-scale legacy codebases (Perl, HTML) and fixing critical UI persistence bugs. Bridging the gap between stats and global production systems.
Independent Project Builder
Engineering reactive business dashboards, spaced repetition systems, and local EDA automation tools. Deployed multiple high-polish web applications using Python and JS.
B.Sc. Statistics
Deep specialization in Probability, Inference, and Sampling Distributions. Applying theory to practical data science projects to solve real-world anomalies.
Selected
Work
DataSense EDA
Offline CSV EDA tool with NLP insights, Pearson correlation engine, and predictive ML models for rapid data analysis. Built for efficiency and depth in local environments.
from datasense import AutoExplorer
df = pd.read_csv('raw_data.csv')
engine = AutoExplorer(df)
engine.analyze_correlations()
NexusSales
Full data pipeline transformation. Ingesting messy CRM data and outputting a reactive business dashboard with actionable statistical insights for sales growth.
MNEMO System
Ebbinghaus-based spaced repetition tool. Features an XP-based leveling system and custom scheduling algorithms to optimize information retention for complex subjects.
