Skip to content
james_tavita

$ whoami_

James Tavita

Software engineer, machine-learning researcher, and technical founder building systems that explain not only what will happen, but why.

I develop custom software, machine-learning systems, causal research, and AI evaluation infrastructure that help organizations make better decisions.

software engineering • causal inference • machine learning • AI evaluation

Open to select consulting, research, and custom technology projects.
DataAssumptionsModelsEvidenceDecisions
02// 02_projects.tsx

Projects

Deep-dive write-ups of real models — architecture, evaluation, error analysis, and limitations.

Regression

NBA Player Performance Forecasting: CatBoost vs. Random Forest

Team analysts, media, and award voters all want a credible answer to "how will this player perform next season" before the season happens — but naive year-over-year projections ignore usage changes, aging curves, and role shifts already latent in the box score.

read case study
Regression

BDS Media Engagement Analytics: What Predicts Views Across a Two-Channel Content Brand

A multi-host YouTube/Instagram media brand — a flagship golf-content channel plus a companion podcast — needed to know which levers actually move engagement (who's talking and for how long, what a title says, how long an episode runs, when it publishes, whether one channel's performance affects the other) instead of relying on editorial instinct alone.

read case study
Classification

Premier League Match Forecasting: Baselines, Challengers, and a Shipped iOS App

Predicting a Premier League match outcome (home win / draw / away win) is a decades-old actuarial problem with a low ceiling — bookmakers and simple rating systems already capture most of the signal. The real question wasn't whether a model could predict outcomes, but whether a more sophisticated model (gradient-boosted trees on rich player and team features) actually beats well-understood baselines like Elo and Dixon-Coles, and whether the whole system could be shipped as a product fans could query directly.

read case study
Classification

Loan Default Prediction: CatBoost on Imbalanced Tabular Credit Data

Given a loan application's financial and demographic profile, predict whether the loan will ultimately be paid back — a standard credit-risk screening problem where the cost of a false negative (approving a loan that defaults) and a false positive (declining a loan that would have been repaid) are asymmetric and business-defined, not something the model itself can resolve.

read case study
Causal Comparison

JIVE: Correcting Many-Instruments Bias in a Movie Box-Office Natural Experiment

Does a movie's opening-weekend ticket sales causally drive its total ticket sales, or does the naive correlation just reflect that both are driven by the same unobserved quality/demand? Opening sales is endogenous — correlated with unobserved quality — so a plain regression of total sales on opening sales conflates the causal effect with that confound.

read case study
Regression

House Prices: A Stacked Ensemble Across CatBoost, XGBoost, and LightGBM

Predict a home's sale price from 79 property features (Kaggle's Ames, Iowa House Prices competition) — a benchmark regression problem where the real difficulty isn't fitting any single model, it's handling a long tail of correlated, mixed-type features (dozens of quality/condition ratings, areas, and categorical construction details) without one encoding scheme handicapping one model family over another.

read case study
Descriptive Study

Who Leads a Mission: 504 Leadership Appointments, Mapped and Tested

Across the 504 missions of The Church of Jesus Christ of Latter-day Saints, is the distribution of leadership appointments anything other than membership spread across a map — and do the leaders drawn from different parts of the world differ?

read case study
03// 03_publications.tsx

Publications

Peer-reviewed research and business case studies I've co-authored.

Peer-Reviewed Paper2026·Journal of Portfolio Management

Oversight Risk: How Committees Shape Portfolios

Scott Condie, Gabriel Lehnardt, James Tavita

PDF
Article2026·Thunderbird Case Series, Harvard Business Publishing (forthcoming)

From Payments to Power: How the PayPal Mafia Shaped Silicon Valley's Venture Landscape

Tom Hunsaker, Abdulaziz Alakeel, James Tavita

04// 04_services.tsx

Ways of Working Together

Custom Software & Data Products

Internal tools, web applications, APIs, dashboards, data pipelines, and decision-support systems.

Machine Learning & Predictive Modeling

Forecasting, classification, ranking, optimization, simulation, model comparison, and production integration.

Causal Inference & Experimentation

Treatment-effect estimation, experiment design, observational studies, difference-in-differences, synthetic controls, instrumental variables, regression discontinuity, matching, and causal machine learning.

AI-Agent Evaluation

Role-specific evaluation, simulation environments, failure analysis, human-versus-agent comparisons, compliance testing, and production monitoring.

Technical Strategy & Prototyping

Product definition, architecture, technical due diligence, rapid prototyping, and translating executive requirements into technical systems.

Published, peer-reviewed researchProduction software in active useFounder — CensiqMachine-learning research experienceEconomics & computer-science background
05// 05_contact.tsx

Have a difficult technical or analytical problem?

Describe the decision, system, or research question you're working on. I can help determine whether it needs custom software, machine learning, causal analysis, AI evaluation, or a combination of them.

Submitting sends this directly to James — no email client required.