Loris Emanuelli

Data Science / Supporting archive

Analytics for decisions

End-to-end analytics pipelines with clear evaluation, model comparisons, and reproducible workflows, framed as a companion to product and mechanical engineering work.

7 results

Tournament probability calibration curve
Data

2026 / Independent ML project

March Madness Prediction Pipeline

Top 1% Kaggle-style tournament model with leakage-safe features, calibrated ensembles, and Stage 2 submissions

MLSports AnalyticsCatBoostLightGBM
Open case->
Predicted career outcome probabilities
Data

2025 / UC Berkeley (IEOR 242A)

NBA Career Trajectory Prediction

Predict career length, survival, and awards from early-career data

MLClassificationRegressionForecasting
Open case->
Service level and shortage comparison
Data

2025-2026 / UC Berkeley Capstone 121

Predict-Optimize E-Commerce Logistics

JD.com demand forecasting and multi-warehouse inventory optimization evaluated on cost, service level, and shortage risk

ForecastingOptimizationAnalyticsSupply Chain
Open case->
Illustrative forecast chart (synthetic)
Data

2025 / ENS Partnership (course project)

Electricity Price Forecasting (ENS Partnership)

Time-series forecasting for day-ahead price spreads

Time SeriesForecastingEnergyML
Open case->
Keras predictions vs data
Data

2025 / UC Berkeley (ME249)

First-Principles vs Keras Neural Networks

Benchmarking custom optimization against RMSprop

MLRegressionOptimizationScientific ML
Open case->
PINN heat-transfer prediction heatmap
Data

2025 / UC Berkeley (ME249)

Custom Loss + PINN Heat Transfer

Physics-inspired training for PV and heat diffusion

PINNScientific MLHeat TransferRegression
Open case->
High-flux PV power surface
Data

2025 / UC Berkeley (ME249)

Solar PV Modeling at High Flux

Extended-range power prediction with neural networks

RegressionEnergyML
Open case->