Ibrahim Denis Fofanah
Data Scientist & AI Researcher
Data scientist and AI researcher at Pace University. I coined Artificial Frictional Unemployment, and built the first machine learning model for crop yield prediction in Sierra Leone. Author of Understanding Agentic AI. I write about agentic systems and applied ML, with a bias toward what actually works, and who gets left out when it doesn't.
98% Accurate and Useless: Six Imbalance Fixes, Measured on a 2% Positive Class
Six models on one 2% positive dataset: the baseline caught 1 of 59 positives, class weights caught 45 at 6% precision, and a balanced random forest predicted zero positives despite the best AUC. Threshold tuning was the only fix that raised F1.
Ibrahim Denis Fofanah·Nov 12, 2026·11 min
Agent Memory Is Three Systems, Not One. Five Papers Prove the Split
Five papers split agent memory into three jobs: factual recall, behavioural rules, and the cost of remembering. Dense retrieval wins long horizons, compaction beats raw transcripts until wording matters, and corrections need rules, not search.
Ibrahim Denis Fofanah·Nov 11, 2026·14 min
Five CTE Traps That Return the Wrong Answer Quietly
Five CTE traps, each measured on one 12-row SQLite table: a random value that ran once, a recursion with no end, a $235 filter-order gap, a table name stolen by its own CTE, and a UNION that ate a path.
Ibrahim Denis Fofanah·Nov 10, 2026·10 min
Sunflower V2 Covers 67 African Languages. The Speech Results Are the Real Story.
Sunbird AI's Sunflower V2 expands from 31 Ugandan languages to 67 across Africa, with speech recognition for 51 languages at 0.227 macro word error on AfriVox-v2. Coverage is growing fast. Whether models know anything about Africa is still an open question.
Ibrahim Denis Fofanah·Nov 9, 2026·9 min
The Best Models Track State Well. At 10,000 Tokens, They Fall to Chance
StateBench tests state tracking across 8 to 64,000 assignments. Frontier models handle the easy tiers, then fall to chance on soluble and general finite tracking once inputs reach 10,000 tokens.
Ibrahim Denis Fofanah·Nov 8, 2026·12 min
Scaling Gave SVM 8 Points and Trees Nothing. I Ran Four Models Raw and Scaled.
SVM went from 88.8% to 97.2% accuracy with one preprocessing line. Random forest moved zero. Logistic regression stopped warning and converged in 20 iterations instead of 1,000.
Ibrahim Denis Fofanah·Nov 7, 2026·10 min
Five String Traps That Rewrite Your Totals. A 12-Row Table Lost $415 Before a Single Clean.
A raw join on city names matched 8 of 12 rows and lost $415 of $1,420. GROUP BY invented four extra cities. COUNT said 11 emails existed; only 10 were real. Five traps, all measured.
Ibrahim Denis Fofanah·Nov 6, 2026·8 min
Korea Just Lent Tanzania $170 Million for AI. The Real Test Is Who Gets to Use It.
Korea Eximbank signed a $170M loan for an AI education centre in Tanzania, the first under the K-AI Package. Days earlier, USTDA put $1.87M into testing a $650M-$1B Nigeria data centre plan. Two financing models, one open question.
Ibrahim Denis Fofanah·Nov 5, 2026·11 min
Agents Find the File and Miss the Cause, and the Gap Grows on Thin Evidence
On 120 real distributed-system bugs, the best agent finds the right file 83.9% of the time but names the causal code block only 67.7% of the time. The gap widens to a 29.8 point drop on reports that name no method and carry no stack trace.
Ibrahim Denis Fofanah·Nov 4, 2026·12 min
Your Email Agent Passed the Phishing Test. Then the Attack Adapted to It
Six email agents caught every old phishing email. Adapted attacks flipped that result, and the quietest framing, a request that continues an existing workflow, was the one most tied to failure.
Ibrahim Denis Fofanah·Nov 3, 2026·10 min
Same Model, Ten Seeds, a 3.5-Point Swing: Why One Split Is Not a Result
Same data, same code, ten split seeds. Logistic regression ranged from 95.8% to 99.3%, and the "winning" model flipped on two seeds. A single split is not a result.
Ibrahim Denis Fofanah·Nov 2, 2026·8 min
East Africa Just Approved a Shared AI Module for Every Degree. Adoption Is Still Voluntary.
On October 31, EAC ministers adopted a regional AI strategy and approved a foundational AI module for undergraduates across eight partner states. Partner states were told to consider adopting it. That word, consider, is the whole story so far.
Ibrahim Denis Fofanah·Nov 1, 2026·9 min
Want an author page like this?
We publish practitioners. Pitch an idea or republish a post from your own blog.