Building Data-Driven Client Relationship Management in Banking with Python

Explore a case study detailing how a small data science team in a large bank transformed a fragmented sales process into a data-driven approach using Python and machine learning. Learn about the challenges faced, including diverse client needs, reduced client coverage due to cost pressures, and uncoordinated sales processes. Discover how Python was instrumental in delivering a production solution that serves advisers and relationship managers continuously. Gain insights into implementing Scikit-learn machine learning pipelines for product affinity in banking and wealth management, using SQL Alchemy for data engineering, leveraging Pandas and Jupyter for development, and employing Luigi pipeline for daily transaction processing. Understand how to extract features from text using NLP with Spacy, deliver machine learning interpretability in production, and develop a reusable Python module for building datasets, developing pipelines, generating monitoring data, and enabling explainability.

Intro
Advanced Analytics in Banking
Relationship Managers
Excel Spreadsheets
Client Planning
Django
Feature Extraction
Sequel Alchemy
Spending Income Profiles
Text Data
Dynamic vs Static
Python Libraries
Pipelines
Machine Learning
Making Recommendations
Tracking Leads
Summary
Questions