UBCI · Case 01
Banking & Regulatory RAG
Can a banking assistant retrieve the right source first without making every CPU request depend on a slow, heavyweight reranker?
83.8%BCT Hit@1
View project 
Available for data science opportunities
Hello,
I'm Slim Dridi
Data Scientist · Banking, risk & applied machine learning
I build useful systems for search, forecasting, and risk—and make their evidence easy to understand.
My work
Selected data science projects
Three concise case studies showing the problem, approach, and measured result.
STEG · Case 02
Network Forecasting & Anomaly Detection
Can short, noisy hourly network histories produce forecasts and anomaly signals that are useful enough for operational monitoring?
4.36Mbps RMSE
View project 
Risk modeling project · Case 03
Credit Card Default Prediction
Can payment history and account behavior identify default risk without hiding minority-class errors behind a comfortable accuracy score?
76.0%balanced accuracy
View project About
I care about what the model changes.
My work sits between statistical evidence and product reality. I care about the question behind a model, the quality of the data feeding it, and whether its output is useful to the person making the next decision.
Based in Ariana, Tunisia. Applied work with UBCI, STEG, Institut Pasteur de Tunis.