My Finance AI
Your finances, quietly understood. Every M-Pesa and bank transaction categorized, forecasted, and budgeted automatically, on real transaction data, not a demo dataset.
The Problem
Most personal finance tools show you what you spent. They don't tell you why it matters, what's coming, or whether you're on track. In Kenya, M-Pesa is how most people move money, and almost no tool treats it seriously as a data source. I built My Finance AI to actually understand spending patterns, not just log them. A model that learns from your own transactions, forecasts where you'll land by month end, and answers questions about your money in plain language.
The Solution
Upload an M-Pesa or bank statement and every transaction gets categorized automatically by a per-user Random Forest model trained on your own spending history. The model runs at 92.4% accuracy across nine categories built around how Kenyans actually spend. Beyond categorization, it forecasts your month-end position per category, flags anomalies, and lets you ask questions about your money in plain language against your real transaction data. It is not a demo. It is running on over 1.2 million KES of real transactions, and the model improves every time you correct a wrong guess.
Product Visuals