> AI Predictions
The AI Prediction Score is a probability (shown as a percentage) for each possible outcome of a market. A score of 70% means the AI thinks that outcome is roughly 70% likely.
It's not a single AI's guess. The score is the combined output of multiple AI models working together, and it updates as new information becomes available. For example, when team news breaks or financial markets move.
Use the score as one input alongside your own research. Not investment advice. Treat it as a second opinion.
Eroteme runs an ensemble of four large language models: Claude, GPT, Gemini, and Grok.
Using multiple models is more reliable than relying on one. Each model has different training data and reasoning patterns, so when they all agree on an outcome, that consensus is a stronger signal than any single model on its own. When they disagree, that disagreement itself tells you the outcome is genuinely uncertain.
Each model is weighted differently depending on the prediction category. Models with better track records in sports get more weight on sports markets; models stronger in financial reasoning get more weight on crypto and stocks.
Before any prediction is generated, Eroteme pulls live data relevant to the category. This is called the data enrichment layer.
For sports predictions, the AI sees current team form, head-to-head records, injury reports, and market signals from sportsbooks. For crypto and financial predictions, it pulls real-time price data and technical indicators. For political predictions, it pulls polling averages and prediction market consensus.
For example, if you ask the AI about a Premier League match, it will know who's injured, what major sportsbooks are pricing it at, recent form, and whether the home team has any tactical advantages. It then weighs all of this against historical patterns before producing a probability.
The AI is calibrated, not infallible. A 70% prediction means the outcome should happen roughly 7 times out of 10, not every time. The AI will be wrong on some predictions. This is normal and expected.
Accuracy varies significantly by category. Sports and financial markets have rich, well-structured data and the AI performs meaningfully better than chance there. One-off world events with limited historical patterns are harder, and the AI is more uncertain.
Eroteme tracks calibration over time and publishes per-category accuracy on the accuracy page so you can see the AI's actual track record.
Not investment advice. Treat the score as one input to your decision.
The Convergence Score is the weighted average of every AI model's individual probability for the same outcome. Models with stronger track records in a given category get more weight in the average.
"Convergence" means how much the models agree with each other. A high Convergence Score means most or all of the models point to the same outcome. That's a strong signal. A low Convergence Score means the models disagree, which usually means the outcome is genuinely uncertain and you should be cautious.
When you see a 78% Convergence Score with all four models aligned, that's much more meaningful than a 78% score where the models are split 60/40.
Yes. No AI system can predict the future with certainty, and Eroteme doesn't claim to.
Even the best-calibrated prediction systems have significant error rates. The Convergence Score reflects uncertainty, not certainty. A 70% score is the AI's honest estimate that the outcome will happen 7 times out of 10, which means 3 times out of 10 it won't.
This is why Eroteme publishes per-category accuracy data openly. We'd rather be honest about the AI's limitations than overclaim and lose your trust.
Scores update as new data becomes available. For sports markets the AI re-runs when team news breaks or sportsbook pricing moves significantly. For crypto markets it updates as price action and on-chain signals change. For political markets it updates as new polls publish.
The exact frequency depends on the category. Fast-moving markets like crypto can refresh multiple times an hour, while a long-range political market might only refresh once a day.
The score you saw when you posted your prediction is what the AI thought at that moment. Later updates reflect new information; they don't change your recorded prediction.
Eroteme actively monitors for systematic bias using calibration tracking across outcome types. If the AI is consistently overestimating one side (for example, always picking favourites in sports), that shows up as poor calibration on a particular outcome bucket and the model weights are adjusted to compensate.
We're honest that no system is perfectly unbiased. Training data has biases. Models inherit them. The best we can do is measure carefully and correct what we find.
The AI currently covers five categories:
- Sports: football, basketball, MMA, and esports
- Crypto and Finance: token price targets, market events
- Politics and Elections: election outcomes, legislative votes
- World Events: geopolitical and macro events
- Entertainment: awards, releases, cultural moments
The AI is most confident in Sports and Crypto, where data signals are richest and patterns repeat. It's least confident in one-off World Events and Entertainment, where there's no historical baseline to calibrate against. Convergence Scores in those categories tend to be lower and more uncertain, and that's by design.
The AI has real advantages: it processes data faster than any human, it sees more sources, and it doesn't have emotional bias when a team you support is involved.
But it has real disadvantages too. It can't know things that aren't in its training data or live data feeds. It can misread context. It can miss late-breaking information. And it's calibrated, meaning it's designed to be roughly right on average, not always right on any individual market.
Treat the Convergence Score as a second opinion, not a replacement for your own judgment. The best predictors on Eroteme combine the AI signal with their own research.
> Forecaster Subscriptions
Some forecasters on Eroteme offer a monthly subscription to their full analysis. Subscribing unlocks everything they publish for subscribers: the complete written reasoning, calibrated probabilities, and any charts or video behind each forecast. Their forecasts, confidence levels, and resolved track record stay public whether you subscribe or not, so you can always judge whether a forecaster is worth it before paying.
Each forecaster sets their own monthly price. You will see the price on their profile and on their subscribers-only posts before you subscribe. Prices in the mobile apps can be slightly higher than on the web because of app store fees.
On the web, open a forecaster's subscribers-only post or their profile and choose Subscribe. Payment is by card, processed by Stripe. In the iOS and Android apps, subscriptions go through your App Store or Google Play account like any other in-app subscription.
Web subscriptions: cancel any time from the forecaster's page or from your subscriptions list in account settings. You keep access until the end of the period you have paid for, and you can resume before it ends if you change your mind. App subscriptions: cancel through your device's subscription settings (App Store or Google Play), the same way as any other app subscription.
Yes. Each subscription is separate, with its own price and its own renewal date, and you can hold as many as you like.
For web subscriptions, contact support@eroteme.io within 7 days of a payment and we will refund it. Later requests are reviewed case by case. For subscriptions purchased through the App Store or Google Play, refunds are handled by Apple or Google through their own request process, and we are not able to issue them directly.
Verified forecasters can turn on subscriptions from the Monetisation section in settings. You set your monthly price, complete identity verification with Stripe, and choose per post whether the analysis is public or subscribers-only. Your forecasts and resolved track record always stay public. Payouts go to your bank account through Stripe. iOS availability for new forecasters can take about a day after you enable subscriptions while Apple reviews the listing; web and Android are available immediately.
> Account
Sign in with your email. No crypto wallet or technical knowledge required. If you already have a Web3 wallet (Metamask, Coinbase Wallet, WalletConnect), you can connect that instead. Both paths give you the same account.
From the mobile app, tap + and choose Get AI Prediction. On the web, use Get an AI Prediction from the side menu.
Search for any Polymarket market, select it, choose your analysis depth and format, and the AI ensemble will generate a full report. Each AI prediction uses one credit from your monthly allowance.
> General
Subscriptions and one-off AI analysis credits.
- App Store and Google Play in the mobile app
- Stripe on the web
Plans:
- Free: $0 · 5 AI analyses per month · no rollover
- Pro: $12.99 / month · 30 analyses · 10 credit rollover · personalised feed · confidence controls
- Elite: $34.99 / month · 100 analyses · 10 credit rollover · everything in Pro · ensemble-weight tuning · per-category signals
Credit packs without a subscription: 10 ($7.99), 30 ($19.99), or 100 ($49.99) one-off credits.
Market results are sourced from official data providers (sports leagues, election commissions, financial data feeds), not from user reports. This means the resolution of a market is based on the same source of truth that bookmakers and news organisations use.
If you believe a result is wrong, you can raise a dispute via the results dispute page. Disputed markets are reviewed manually and either confirmed, corrected, or voided depending on the evidence.
For the platform's current security posture, see the security page.