Case Study 04 IBM
MBA Product Manager Aug — Dec 2023 New York, USA

Streamlining Stock Research with Generative AI

Compressing 3 hours a day on research to minutes.

EnterpriseAI/MLGenAIFinTech
Artifacts
01 / 04
Problem

What we were actually solving

Stock analysts tasked with explaining anomalies in stock performance had to manually set thresholds, sift through news articles one by one, and summarize findings by hand, a process that was both time-consuming and prone to error. Investment bankers downstream were dependent on this slow, manual pipeline to make decisions.

Process

How we got there

  1. Step 01
    User Research

    Conducted user research with stock analysts and investment bankers to map the pain points across their workflow.

  2. Step 02
    Journey Mapping

    Identified four bottlenecks: anomaly detection, news article sourcing, summarization, and follow-up Q&A.

  3. Step 03
    Proof of Concept

    Built the PoC in three stages using IBM watsonx tools: anomaly detection, article extraction , GenAI summarization, and RAG-based Q&A using IBM's Granite model.

  4. Step 04
    Optimization

    Solved context window limitations through LangChain-based chunking after testing spaCy and manual approaches.

  5. Step 05
    Documentation

    Produced a watsonx Playbook for IBM SkillsBuild.

Solution

What shipped

An end-to-end stock anomaly analysis workflow replacing the manual process: AutoAI detects anomalies from historical stock data, Jupyter Notebook automatically sources and extracts relevant news articles, Prompt Lab summarizes events causing anomalies, and RAG-powered Q&A enables analysts to drill deeper into any finding.

Outcome

The numbers

3h/day
saved per stock analyst on research
2M
students and underrepresented communities reached
1st
watsonx example for IBM SkillsBuild