Model forecasts built from public data, for elections, sport and markets. Each page states the date its forecast was made.
Aggregate net units, ROI and open hypothetical positions across sports and elections, with matched midpoint / ask-plus-fee comparisons and the individual breakdowns.
Every upcoming forecast on one page: NBA, NFL, rugby league and cricket games beside the Kalshi and Polymarket prices, the Victorian election and the NBA season, with recent results.
Two-party-preferred poll average simulated to a placeholder May 2028 date and applied division by division to the 2025 AEC results (state effects, seat noise, crossbench holds): Labor and Coalition majority odds, hung parliament, seat map, against Kalshi; 2025 backtest.
First-round polls for the most-polled candidate set, simulated with a backtested error model; the two largest draws go to a runoff priced from published head-to-head polls or a stated transfer table. Runoff pairs, winner odds, a département map under proportional swing from 2022, against Kalshi and Polymarket; 2022 backtest.
National polls simulated with a backtested error model and allocated by Sainte-Laguë with the 5% threshold: largest party, coalition arithmetic, threshold risk, a state map by proportional swing, against Kalshi; 2025 backtest.
Legislative Assembly, 13 March 2027: the 2023 result swung by the poll average with One Nation placed from federal booths, optional-preferential exhaustion, a district map, seat distributions and Kalshi's Labor-majority contract; backtested on 2023.
National polls projected province by province (proportional swing from 2023) and allocated by D'Hondt in the 52 constituencies: PP and Vox majority odds, largest party, investiture arithmetic, against the markets; 2023 backtest.
GB polls swung seat by seat from the 2024 result (proportional swing, first past the post in 632 constituencies, Northern Ireland held): largest party, Reform and Labour majority odds, a constituency map, against Kalshi; due by August 2029.
One dashboard for Senate and House research, the recorded Senate polling study and prediction-market prices, with independent source dates and coverage labels.
7 November: national party-vote polls, MMP threshold risk and explicit electorate-overhang scenarios. Coalition arithmetic is conditional; electorate outcomes and government formation are not forecast.
All 88 Legislative Assembly seats for 28 November 2026: maps, win probabilities, seat counts, the Kalshi markets and how the model did in 2018 and 2022.
Interim winner-call evaluation, matched market comparisons, all forecast misses and unresolved results. 5 November 2026.
Declared candidates and potential presidential nominees, sourced status, and separate Kalshi and Polymarket nomination and general-election prices.
Reported party and bloc seats against the frozen pre-election forecast; verified market settlements and the contracts still awaiting resolution.
The final recorded forecast before polls opened, preserved separately from the result review.
Inflation, wages, the labour market, GDP, household spending, housing, RBA and bond rates, the dollar and the ASX from ABS releases, RBA tables and market data, with Kalshi's price for the next RBA decision.
The listed insurers (prices, fundamentals, price-sensitive announcements), APRA's quarterly general insurance statistics (profit, premiums, loss ratios by class and state, capital), the Insurance Council's catastrophe declarations and historical losses, insurance and claims-cost items in the CPI, and the regulators' releases.
A written report on the insurance page's indicators as at 12 October 2026: industry profit down 31%, catastrophe losses nearly doubled, premium inflation rising again, Allianz Australia's recovery from a loss-making December quarter, complaints still rising.
The current men's Test scored every 30 overs against the sessions par and the Bayesian par: cumulative runs against expectation per innings, each block's runs and wickets, and the block table.
Tests, T20Is and ODIs on one page: team and player rankings, upcoming matches, matchup scenarios, player value and model validation, with men's and women's coverage.
Separate readiness and development screens for Sheffield Shield players, with role-specific Test comparisons, uncertainty and match evidence. Research prototype.
Live player impact revisions, minutes, uncertainty and evidence above or below preseason expectation; searchable by player and team.
Live 2026–27 forecast updated nightly from results: standings, playoff and title odds, next games; the October 17 preseason forecast against Kalshi; luck and research.
Every earlier NBA forecast as published: daily live forecasts, the October 17 Board and interactive page, the October 7 original.
Current-season-only merit ratings, our All-Star and award selections, uncertainty and continuation projections; last season is used only as the Most Improved benchmark.
Career wins above replacement, a leaderboard, career comparisons and player projections.
Model fair salary from projected wins above replacement against listed 2026–27 salaries.
Team and conference rankings, projected wins and market comparisons.
The in-season update from game margins, the pre-registered backtest against preseason ratings and record pace, single-game comparison with closing lines, and the adjustments that did not help.
The October 17 model, experiment results, limitations and next tests, with what has changed since.
Archived original predictions.
Versioned Bayesian polling models with pollster effects, election-day uncertainty, conditional seat sensitivities and historical development comparisons. Baseline forecasts retained.
Questions worth testing, by sport, with links to the write-ups as each is done.
A pre-registered Bayesian study of 1,800 federal and state polls since 1998: the industry's polling-day error, how opinion drifts before an election, house effects, and a 'time for a change' prior.
The session-block par refitted as a multilevel count model in Stan: held-out error and posterior predictive checks against the ridge and cell pars, where the variation lives, and carry once an innings effect is pooled.
A resource table fitted to each format and sex against the official Standard Edition, and whether the targets actually set in rain-affected chases have favoured one side.
A pre-registered test of whether a player's recent form in T20 predicts their next one-day match (and the reverse) beyond their own history in that format, batting and bowling, men and women.
A pre-registered test at two time scales: do recent innings predict the next beyond a player's level, and within an innings is the ball after a boundary (or a wicket) better than the player's average ball?
Four isolated extensions tested as pre-registered development studies: an annual scoring level in the Bayesian Test par, basketball totals through possessions and rotations, club player ratings in franchise T20, and WNBA-specific forecast weights. None clears the bar; the dynamic par is a prospective candidate.
A par for every 30-over block of a Test innings from the match state and the two sides, recent Tests scored block by block, and whether a block above par predicts the next.
The hazard-binomial wickets model registered and its beta-binomial expansion tested against the cell mean under a rule fixed in advance, on the same held-out years as the Bayesian-par note (development evidence).
A pre-registered test of adding a per-match conditions effect to the player ratings: does crediting runs relative to how everyone else scored that day predict matches better, and how much do the rankings move?