Dynamic Python Developer with a proven expertise in Data Analytics, Machine Learning, and Backend Software Development. Demonstrates a compelling history of achieving measurable results through strategic application of technical proficiency. Seeking opportunities to apply a diverse skill set and extensive experience in data analysis to contribute to impactful projects. Proficient in translating complex datasets into actionable insights and adept at crafting effective business solutions through sophisticated data visualization techniques. Possesses a strong foundation in web development and remains abreast of cutting-edge technologies. Committed to delivering excellence and contributing to the success of forward-thinking organizations. here.
Web Mapping confirmed cases of the Novel Corona Virus in the U.S.
Time to Event analysis of different drug trials used to treat drug reocurrence. Measured average lifespan and probability of death at time T.
Demonstration of FAIR data principles applied to crop field trial data. The tool makes maize phenomic field trial data from the Genomes To Fields Initiative accessible and findable through the search interface below.
NLP on 152 semiconductor 10-Ks pulled from the SEC EDGAR API: Loughran-McDonald tone and year-over-year cosine similarity (“Lazy Prices”), joined in DuckDB SQL to forward returns and XBRL revenue. Finding: Risk Factors sections doubled since 2015 (median 7.4k → 15.2k words), yet year-over-year cosine similarity stays ~0.98: firms mostly copy-paste.
TF-IDF + NMF topic modeling on 356K CFPB complaint narratives for 10 banks and fintechs, rolled up into quarterly alternative-data signals in DuckDB SQL. Finding: Cash App’s 36x complaint spike in Q1 2025 was 77% one copy-paste template, starting the week of the CFPB’s enforcement order.