{"id":2569,"date":"2025-02-18T19:29:14","date_gmt":"2025-02-18T12:29:14","guid":{"rendered":"https:\/\/mintea.blog\/?p=2569"},"modified":"2025-03-05T10:23:55","modified_gmt":"2025-03-05T03:23:55","slug":"2569","status":"publish","type":"post","link":"https:\/\/mintea.blog\/?p=2569","title":{"rendered":"Bridging the GAP: Business Expert meets ML @UEH_Sharing_2025-Feb-19"},"content":{"rendered":"

I recently had the chance to speak with MBA students at the University of Economics about the vital role of business experts in data and machine learning applications. Rather than focusing on technical details, I emphasized how their industry knowledge and strategic thinking can drive successful ML projects. Through a case study on a risk manager using ML for a scorecard project, I illustrated how business professionals can leverage data-driven insights without needing deep technical expertise. In this blog, I\u2019m sharing my slides and key insights to help others understand how to apply ML effectively in a business context.<\/p>\n_2025-02-19_UEH (ML-Banking)<\/a>\n

Q&A:<\/strong><\/p>\n

#1 —————————————————<\/span>
\nStudent asked<\/strong>: “I’m working in a fintech company, offering stock trading, what is the variables of the ML model?”<\/span><\/p>\n

Tri answered:<\/strong>
\nFirst, the question should be reframed. Instead of asking, \u201cWhat are the variables of the model for a fintech company?\u201d, you should ask:\ud83d\udc49 \u201cI want to protect and grow the business. How can I apply Machine Learning?\u201d<\/span><\/p>\n

Step 1<\/strong>: Understand Your Business Portfolio & Revenue Sources<\/span>
\nBefore jumping into ML, you need to analyze your business fundamentals:<\/span>
\n. What are the sources of income? (e.g., trading fees, spreads, subscriptions, margin lending)<\/span>
\n. Who are your customers? (e.g., retail traders, institutional investors, high-frequency traders)<\/span>
\n. How do they behave? (e.g., trade volume, retention rate, churn rate, deposit patterns)<\/span><\/p>\n

Step 2<\/strong>: Analyze Data Across Multiple Dimensions<\/span>
\nLook at historical data from different perspectives:<\/span>
\n. By stock: Which stocks drive the most trading activity?<\/span>
\n. By customer segment: Are high-frequency traders more profitable than long-term investors?<\/span>
\n. By demographic: Are younger users trading more actively than older ones?<\/span>
\n. By trend: Is there a slowdown in a particular segment? Are certain products underperforming?<\/span><\/p>\n

Step 3<\/strong>: Identify Key Business Challenges & Make a Case for ML<\/span>
\nOnce you detect issues like a decline in trading volume, an increase in churn, or low engagement in certain segments, you can start building a business case:<\/span>
\n. Why do you need ML?<\/span>
\n. What problem will it solve?<\/span>
\n. How will it increase revenue or reduce risk?<\/span><\/p>\n

Step 4<\/strong>: Discuss with Management & Defend Your Idea<\/span>
\n. Present your findings and explain how ML can be a strategic tool:<\/span>
\n. For retention: ML models can predict which users are likely to stop trading and suggest personalized offers.<\/span>
\n. For growth: AI-driven recommendations can increase trading activity.<\/span>
\n. For risk management: Fraud detection models can prevent financial losses.<\/span><\/p>\n

Step 5<\/strong>: Dive into ML Research (or Ask ChatGPT!)<\/span>
\nAt this point, you can explore relevant ML models:<\/span>
\nRead industry papers, case studies, or competitor strategies.<\/span>
\nUse AI (like ChatGPT) to get insights on which ML models suit your business needs.
\nOnboard vendors (3 quotations from 3 vendors \/ of your in-house modelling team) then you can learn of their proposals.\u00a0<\/span>
\n\ud83d\udca1 Takeaway: The right approach is business-first, data-driven, and ML-enabled\u2014not just focusing on model variables but understanding the real business impact of ML. \ud83d\ude80<\/span><\/p>\n

Now, let’s check with ChatGPT further regarding the model:
\nPrompt:<\/span>
\n<\/strong><\/em>I’m working in a fintech company offering stock trading service to customer with flexible trading amount and volume,
\n1. what is the main source of revenue for my business model?
\n2. suggest me how to apply Machine Learning to grow the business, retain customer with the detail case study.<\/p>\n

ChatGPT:
\n<\/strong><\/em><\/span>1. Main Sources of Revenue for Your Fintech Stock Trading Business
\nYour company likely generates revenue from several key streams:<\/p>\n