ML Engineering

Eighteen focused ML systems spanning healthcare, agriculture, retail, finance, real estate, and beyond. Each project tackles a real domain problem with a deliberate choice of method — from deep learning and ensemble models to non-parametric regression and unsupervised clustering.

17

ML Engineering
Systems

9

Domains

12

Datasets &
Real-World Problems

Domain

Healthcare

Clinical risk prediction · Diagnostic classification · Patient data modeling

ML Engineering Healthcare
👁️

Diabetic Retinopathy Classifier

Logistic Regression

A binary classification model predicting diabetic retinopathy probability from retinal image features. Uses backward elimination and AIC for variable selection on 1,151 patient records — providing a clinically interpretable probability score for early DR detection.

⭐ Clinically interpretable probability score for early diabetic retinopathy detection

R Logistic Regression AIC Hosmer-Lemeshow
View Project →
ML Engineering Healthcare
🫀

Coronary Heart Disease Risk Classifier

Ensemble Classification

A binary classification system predicting 10-year coronary heart disease risk from patient vitals and lab results. Benchmarks Random Forests against Mixture Discriminant Analysis across 10 random seeds on 4,080 Framingham Heart Study patients for consistent, reliable predictions.

⭐ 84.3% classification accuracy. RF outperformed MDA with lower variance across seeds

R Random Forest MDA caret
View Project →

Domain

Computer Vision & NLP

Spatial & temporal learning · Sequence modeling · Architecture implementation

ML Engineering Computer Vision
🎥

DeepVision: Video Analysis

ConvLSTM Architecture

A ConvLSTM deep learning model that combines spatial feature extraction with temporal sequence modeling for automated video classification. Processes raw video frames through an OpenCV pipeline and outputs class predictions for video-heavy operational workflows.

⭐ 84% accuracy, 97% AUC. Combines spatial and temporal learning in one model

TensorFlow OpenCV ConvLSTM CNN
View Project →
ML Engineering NLP
🤖

Transformer: Encoder–Decoder Architecture

From-Scratch Implementation

A full Transformer architecture built from scratch in PyTorch — no Hugging Face, no abstraction shortcuts. Covers positional encoding, multi-head self-attention, feedforward layers, encoder and decoder blocks, and the complete encoder–decoder stack with configurable depth and heads.

⭐ Full architecture from scratch — every component implemented in detail

PyTorch Lightning Attention Python
View Project →

Domain

Retail & Commerce

Demand forecasting · Customer behavior · Market basket analysis

ML Engineering Retail & Commerce
🛍️

Product Purchase Predictions

CNN+LSTM · Multi-Output

A CNN+LSTM hybrid pipeline forecasting per-product daily purchases using lagged and calendar features. Predicts next-day demand for multiple products simultaneously in a single forward pass — enabling smarter inventory planning and procurement decisions.

⭐ Multi-output sequence model predicting demand for N products in a single forward pass

PyTorch CNN+LSTM pandas scikit-learn
View Project →
ML Engineering Retail & Commerce
🛒

Association Rule Mining

Apriori · Market Basket

An unsupervised market basket analysis system applying the Apriori algorithm to uncover hidden product co-purchasing patterns from transaction data. Generates rules ranked by support, confidence, and lift — surfacing actionable bundling and cross-sell opportunities.

⭐ Actionable co-purchase patterns with high-lift rules for cross-sell strategy for the retail domain

Python mlxtend Apriori pandas
View Project →
ML Engineering Retail & Commerce
🏥

PolicyPredict

Deep Learning · Neural Net

A deep neural network pipeline predicting insurance policy purchase likelihood from customer data. Combines scikit-learn preprocessing with TensorFlow model training to output purchase probability scores for targeted marketing and personalized policy recommendations.

⭐ 70% accuracy · 85% ROC-AUC · Deep learning outperforms classical baselines

TensorFlow scikit-learn pandas Python
View Project →
ML Engineering Retail & Commerce
🏷️

PolicyPredict Lite

Classical ML · Interpretable

A lightweight scikit-learn pipeline predicting insurance purchase behavior using Logistic Regression, Random Forests, and SVMs. Built as the classical ML counterpart to PolicyPredict — directly comparing interpretability and performance tradeoffs against the deep learning version.

⭐ Side-by-side deep vs. classical ML comparison on the same insurance purchase dataset

Logistic Regression Random Forest SVM
View Project →

Domain

Finance & Economics

Customer targeting · Economic forecasting · Behavioral pattern mining

ML Engineering Finance & Economics
🏦

Bank Marketing Targeting Engine

Apriori · Association Rules

Association rule mining on 41,188 Portuguese bank clients to identify which attributes drive term deposit subscriptions. Rules ranked by standardized lift surface the most actionable client segments for targeted campaign outreach and rejection avoidance.

⭐ 13 rules generated. Marital status and prior contact identified as top subscription drivers

R arules Apriori Standardized Lift
View Project →
ML Engineering Finance & Economics
📈

GDP Forecasting Engine

Spline Regression

A non-parametric spline regression system modeling China's GDP growth from 1960 to 2014. Compares standard cubic splines across varying degrees of freedom against smoothing splines across bandwidth parameters — analyzing the bias-variance tradeoff for complex economic trend forecasting.

⭐ Smoothing splines outperformed cubic splines for exponential economic growth modeling

R Cubic Splines Smoothing Splines
View Project →

Domain

Agriculture

Crop classification · Quality control automation · Agricultural ML

ML Engineering Agriculture
🌾

AgriGrain: Grain Type Classification

Ensemble · Neural Networks · R

A multiclass grain classification system built entirely in R, comparing five algorithms — Bagging, Random Forests, Boosting, MDA, and ANNs — on geometric and shape features. Automates grain type identification to reduce manual inspection effort in agricultural quality control.

⭐ Random Forest and Boosting consistently outperformed baseline classifiers across all grain types

R Random Forest Boosting ANN caret
View Project →

Domain

Real Estate

Property value prediction · Regularization benchmarking · Non-linear modeling

ML Engineering Real Estate
🏘️

Boston House Value Prediction

Ridge · LASSO · LSLR

A regression benchmark comparing Least-Squares, Lasso, and Ridge on the Boston Housing dataset across 506 properties and 13 predictors. Demonstrates regularization benefits in the presence of multicollinearity — with Lasso producing the most parsimonious model by excluding INDUS and AGE.

⭐ Lasso MSE=23.63 — best performer. Excluded INDUS and AGE for most parsimonious model

R glmnet LASSO Ridge Cross-Validation
View Project →
ML Engineering Real Estate
🏙️

Taipei House Value Prediction

GAMs · MARS · Ridge

A non-linear regression benchmark comparing GAMs, MARS, and Ridge on 414 Taipei City properties. Exploits known non-linearities — house age takes a parabolic shape, MRT distance is inversely proportional to price — to demonstrate where non-parametric methods outperform linear regularization.

⭐ GAMs MSE=58.8 — best performer. MRT distance identified as dominant price predictor

R GAMs MARS Ridge Cross-Validation
View Project →

Domain

Engineering & Materials

Structural prediction · Forensic classification · Materials science ML

ML Engineering Engineering & Materials
🏗️

Concrete Compressive Strength Predictor

Tree Ensemble Regression

A tree ensemble regression pipeline predicting concrete compressive strength from mix ingredients — replacing time-consuming lab testing with rapid ML predictions. Benchmarks Bagging, Random Forests, and Gradient Boosting on 1,030 specimens across 8 predictors.

⭐ Boosting significantly outperformed Random Forest and Bagging

R Gradient Boosting Random Forest Bagging
View Project →
ML Engineering Engineering & Materials
🔬

Glass Forensic Classifier

Unsupervised Clustering

An unsupervised clustering system classifying forensic glass samples from crime scenes by chemical composition. Compares Hierarchical Clustering, K-Means, and Gaussian Mixture Models on 214 samples across 9 chemical variables to support forensic evidence identification.

⭐ K-Means best performer. Separated headlamp glass from all other types

R K-Means GMM Hierarchical Clustering
View Project →

Domain

Public Health & Sustainability

Population health modeling · Environmental prediction · Non-parametric methods

ML Engineering Public Health & Sustainability
🌍

Life Expectancy Trend Modeler

KNN · Kernel Smoothing

A non-parametric regression system modeling Russian life expectancy trends from 1800 to 2016. Compares k-NN regression and Gaussian kernel smoothing across a range of hyperparameters — analyzing the bias-variance tradeoff for complex non-monotonic time-series data.

⭐ Kernel smoothing preferred for smoother boundary behavior and better handling of fluctuations

R KNN Regression Kernel Smoothing
View Project →
ML Engineering Public Health & Sustainability
⛽

Fuel Economy Prediction Engine

LASSO · MARS

A comparative regression system predicting vehicle fuel economy from 7 characteristics on 392 vehicles. Benchmarks LASSO against MARS — demonstrating MARS's advantage in handling non-linearity and variable interactions while both address multicollinearity in the Auto MPG dataset.

⭐ MARS MSE significantly outperformed LASSO MSE. Captured non-linear interactions

R LASSO MARS glmnet earth
View Project →

Domain

ML Tooling

Model benchmarking · Hyperparameter optimization · Automated model selection

ML Engineering ML Tooling
🌲

OptiTree: Tree Model Benchmarking

PSO · Multi-Model Benchmarking

A model benchmarking framework comparing seven tree-based classifiers — Decision Tree, Random Forest, AdaBoost, Gradient Boosting, LightGBM, XGBoost, and CatBoost — under automated PSO-based hyperparameter search. All experiments tracked via MLflow for reproducible comparison and downstream deployment.

⭐ PSO-tuned models outperformed default settings. All experiments logged in MLflow for reproducibility

XGBoost CatBoost LightGBM MLflow PSO
View Project →