Project Library

Machine learning, analytics, software tools, and browser experiments by Daniel Short.

  • 15+project builds
  • 4focus areas
  • SQLPython and BI
  • Livedemos and case studies

Project results

Loading projects...

Smart Sentence Retriever

NLP Embeddings & Serverless Retrieval: I wanted a fast way to retrieve sentences that answer a question even when the wording doesn't match exactly.

NLP Embeddings & Serverless RetrievalMachine LearningAutomationPython

Chatbot (LoRA + RAG)

RAG Chatbot Fine-Tuned with LoRA: The project needed to show both sides of a tourism chatbot decision: a custom fine-tuned model that could learn…

RAG Chatbot Fine-Tuned with LoRAMachine LearningAutomationPython

Shape Classifier Demo

Handwritten Shape Recognition: I wanted a model that can tell what shape someone drew.

Handwritten Shape RecognitionMachine LearningPythonPyTorch

UFO Sightings Dashboard

Tableau Geospatial Analytics: I wanted to see patterns in UFO sighting reports across the U.S.

Tableau Geospatial AnalyticsVisualizationAnalyticsTableau

COVID-19 Outbreak Drivers

Python XGBoost & SHAP: Using 2020-2023 HHS hospital-capacity data, I built an early-warning model to flag states at risk of crossing 90% ICU utilization in…

Python XGBoost & SHAPAnalyticsPythonAWS

Empty-Package Shrink Dashboard

Excel Forecasting & BI: Empty-package shrink was growing, and leaders needed a single view of trends, hotspots, and forecasted risk across locations and…

Excel Forecasting & BIAutomationAnalyticsExcel

Handwriting Legibility Scoring

PyTorch CNN Fine-Tuning: My wife says my handwriting is hard to read. I wanted an objective score.

PyTorch CNN Fine-TuningMachine LearningPythonPyTorch

Synthetic Digit Generator

Variational Autoencoder: I wanted to generate new handwritten digits, not just recognize them.

Variational AutoencoderMachine LearningPythonVAE

Sheet Music Watermark Removal & Upscale

UNet & VDSR Pipeline: I needed clean, readable sheet music. Most of what I could find was low-res and watermarked.

UNet & VDSR PipelineMachine LearningPythonComputer Vision

Delivery Tip

Excel Geo-Analytics & Optimization: I wanted to know which shifts and neighborhoods lead to better tips.

Excel Geo-Analytics & OptimizationAnalyticsExcelPower Query

Store-Level Loss & Sales ETL

SQL ETL + Anomaly Detection: Leaders needed one reliable way to compare security incidents, theft hotspots, and sales signals without stitching together…

SQL ETL + Anomaly DetectionAutomationAnalyticsSQL

Pizza Tips Regression Modeling

Excel Analytics & Regression Modeling: Tips varied a lot by neighborhood and housing type. I wanted to see what actually drives them.

Excel Analytics & Regression ModelingAnalyticsExcelStatistics

Baby Name Predictor

Python ML Pipeline: My wife asked me to suggest baby names. I wanted something that learns her taste instead of guessing.

Python ML PipelineMachine LearningPythonscikit-learn

Pizza Delivery Dashboard

Tableau Analytics & Forecasting: I needed a Tableau dashboard that could compare delivery zones, earnings, timing, and tip patterns quickly enough to…

Tableau Analytics & ForecastingVisualizationAnalyticsTableau

Nonogram Solver

Reinforcement Learning (RL): I wanted to see if an RL agent could learn to solve Nonogram puzzles.

Reinforcement Learning (RL)Machine LearningPythonPyTorch

danielshort.me

Responsive Portfolio Site: I needed a fast site to show my work, especially on mobile.

Responsive Portfolio SiteProductVisualizationHTML