Consumer Complaint Analytics

Jul 10, 2026 · 1 min read
projects

Jun 2026 – Jul 2026

  • Engineered a full NLP pipeline on the CFPB Consumer Complaint Database (8+ GB) using TF-IDF and logistic regression.
  • Made an automated complaint classifier, which achieved ~0.87 accuracy.
  • Identified the growing share of templated filings and distinguished automated volume from genuine consumer harm using advanced statistical analysis, such as Cramér’s V and the chi-square test of independence.
NLP Machine Learning Text Classification Statistical Analysis
Porush Yadav
Authors
Porush Yadav

Hi! I am Porush Yadav. I have graduated from IIT Kanpur with a BS-MS Dual Degree in Mathematics and Scientific Computing. I have Worked at Axis Bank on an image recognition system that leverages neural networks to automate document classification and enhance data extraction. Before that, I interned at Samsung R&D Institute India, eJET systems, and EZ Technologies, where I worked on machine learning applications in signal data compression, recommendation systems, classification systems, and image recognition.

I look forward to leveraging AI and ML expertise to develop impactful solutions that can solve real-life problems.