How manjushatr/customerbehavioranalysis works
Project type and purpose
• From the file tree and the README, this is a data-mining / customer-behavior analysis project composed almost entirely of Jupyter notebooks (with one R script).
• Its goal is to ingest customer data, perform data understanding, feature engineering, then apply clustering, association-rule mining, classification (loan-decision modeling), and finally produce insights and visualizations.
File structure
• Top-level notebooks reflect distinct phases:
• DataUnderstanding.ipynb
• CustomerBehaviorAnalysis (parts 1–4)
• ClusteringAnalysis.ipynb
• AssociationRules.ipynb
• LoanDM.ipynb (loan decision modeling)
• lazypredictsample.ipynb (automated ML experiment)
• “FinalWork” subdirectory re-organizes select notebooks and includes the raw CSV in FinalWork/Data.
• aprioriassign.R shows there is at least one R-based association rule implementation.
• README.md gives only the project title.
Extract additional insights from the README
• We infer the tech stack: Python, Jupyter, pandas, scikit-learn, mlxtend (for apriori), plus R for one step.