Freelancers using scikit-learn in Surabaya
Freelancers using scikit-learn in Surabaya
Sign Up
Post a job
Sign Up
Log In
Filters
2
Projects
People
kaze nesia
Surabaya, Indonesia
Full-Stack Data Specialist | Automation & Predictive
Follow
Message
Full-Stack Data Specialist | Automation & Predictive
0
AI Student Success Intelligence Platform A twelve‑module analytics platform analyzed 50,000 learners across six countries to predict dropout, model engagement, and simulate interventions, finding that a composite Student Engagement Index (SEI)—built from Time Commitment, Academic Quality, Platform Activity, and Social Learning—is the strongest predictor of dropout (behavior beats demographics), an ensemble of XGBoost/LightGBM/CatBoost achieved 99.72% AUC and F1 = 0.9522, risk tiers were highly precise (Low Risk = 0.0% dropout; Critical Risk = 99.7%), multi‑dimensional “Full Interventions” produced the largest simulated risk reductions, and correcting a data‑leakage issue (attendance proxy) was essential to preserve model integrity.
0
234
0
Crypto Market Intelligence & Alpha Signal Engine An end-to-end Colab pipeline ingests market feeds, engineers 43 signals, detects regimes (KMeans/HMM/GMM), models 24‑hour alpha with a Random Forest (ROC‑AUC 0.7714), flags anomalies (Isolation Forest/Autoencoders), and backtests strategies; key findings: the SELL signal is highly precise (only 5.14% of SELLs rose next day), anomalies are often bullish (36.87% up vs 25.49% normal), price‑level context and regime probabilities drive predictions, and the model favors low‑volatility, defensive assets during downturns.
0
183
0
Global Retail Intelligence System: Product Success Prediction and Strategic Market Analysis A multi-stage ML pipeline analyzed 44,888 Adidas SKUs using XGBoost and Random Forest to predict product success, demand trajectories, and stockout risk, finding that subcategory is the dominant success driver (~6× more explanatory than price, discount, or geography), the Success Classifier reached 94.3% accuracy and the Stockout Risk model 0.99 ROC‑AUC, 42.5% of products carry markdowns with deep discounts (≥30%) often eroding margins, 323 high-performing SKUs are under‑distributed and present near‑term expansion opportunities, the Budget tier outperforms Premium/Luxury in conversion to high performers, and 653 SKUs were flagged as high demand with elevated stockout risk requiring urgent replenishment.
0
132
0
AI-Driven Global Smartphone Sales Strategy Optimizer An end-to-end ML project used four years of global sales data and 132,000+ simulations to optimize pricing across 52 countries, identifying the exact product, channel, and price to maximize profit. Key findings: the “Discount Myth”—discounting has almost no effect on volume but erodes margins; switching from blanket 20% discounts to AI‑optimized pricing yields a 15.1% revenue gain (about $73,993 preserved per simulation). The B2B channel is optimal in 90% of markets. The production XGBoost model achieves 99.73% accuracy, and ultra‑premium products (notably the Samsung Neo QLED 8K) consistently generate the highest revenue.
0
131
scikit-learn
(5)
Follow
Message
Explore people
