{"id":8935,"date":"2026-06-05T18:35:59","date_gmt":"2026-06-05T22:35:59","guid":{"rendered":"https:\/\/www.squawka.com\/us\/?post_type=news&p=8935"},"modified":"2026-06-05T19:14:26","modified_gmt":"2026-06-05T23:14:26","slug":"squawkas-ai-predictor-methodology","status":"publish","type":"news","link":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/","title":{"rendered":"AI Predictor Methodology: How Our Score Picks Work"},"content":{"rendered":"\n\n

This page sets out the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it deliberately does not try to do. It is a transparent system, not a black box. The Predictor puts a predicted scoreline alongside bet365’s price for every match at the 2026 World Cup<\/a>, so you can see, match by match, where the data agrees with the market and where it does not.<\/p>\n\n\n\n

Inside the AI Predictor methodology<\/h2>\n\n\n\n

Honest framing first. The Predictor is not a trained machine-learning model with hundreds of layers and a billion parameters. It is a weighted-features engine: a system that takes a defined set of inputs, blends them in defined proportions, and outputs a predicted scoreline plus a margin of implied edge against the market.<\/p>\n\n\n\n

The “AI” in the title is doing real work. It is an automated system making predictions from data. But it is worth being clear about what is behind it. A reader who clicks expecting an opaque neural network is going to be disappointed. A reader who clicks expecting a system they can interrogate, criticise, and hold accountable across a 64-match tournament is in the right place.<\/p>\n\n\n\n

Everything below is the inside of the box.<\/p>\n\n\n\n

What the AI Predictor weighs<\/h2>\n\n\n\n

Three things feed the Predictor for every match.<\/p>\n\n\n\n

The market.<\/strong> We use bet365’s pre-match 1X2 price and the correct-score market as the anchor. The market is the most efficient single signal on soccer, particularly close to kickoff. It reflects sharp money, public information, and a long history of pricing similar fixtures. Bet365’s price gets converted to an implied probability distribution over every plausible scoreline, anchored on the over\/under goal line, and that becomes the starting point.<\/p>\n\n\n\n

The advanced data.<\/strong> For most teams in the tournament, where the confederation’s qualifying or continental competition is covered by our data feed, we pull recent-form numbers from the 120 Football data platform: shot generation, shot quality, pass accuracy, final-third entries, big chances created and conceded, ball-loss rates, and set-piece threat. These are the same advanced metrics that drive the editorial side of Squawka US match previews, and the same family of data Squawka has been building visualisations from for over a decade.<\/p>\n\n\n\n

A strength prior.<\/strong> Qualifying record and FIFA ranking go in as a baseline, calibrated against group-stage performance from prior World Cups. The prior matters most when the market is thin, early in the tournament, before sharp money has had a chance to settle on every fixture. It matters less once each side has played a competitive match in front of the model.<\/p>\n\n\n\n

A prediction-market cross-check.<\/strong> Where Kalshi<\/a> or Polymarket<\/a> prices a corresponding contract on the fixture, typically match winner or advance-from-group, the model uses that price as a secondary sanity check on the bet365 prior. Prediction markets are CFTC-regulated event contracts rather than sportsbook bets, and they read slightly differently from book prices: deeper liquidity over longer windows, no overround, and a tighter consensus on outcome probability. Where the two markets diverge meaningfully, the rationale prose flags the gap. The bet365 prior remains the anchor; the prediction-market read is the cross-check.\n\n\n\n\n

How the AI Predictor picks a scoreline<\/h2>\n\n\n\n

The Predictor’s pick is a weighted blend. Forty per cent of the weight sits with the market prior, which is bet365’s view of the match. Thirty-five per cent goes to the advanced-data delta, which is the difference between the two sides on the features that most divide them in this fixture. Fifteen per cent is the baseline strength prior. Ten per cent is a head-to-head adjustment, applied only when the two sides have met often enough in recent years for the sample to mean something.<\/p>\n\n\n\n

Those four signals get combined into a probability distribution across plausible scorelines, including 1-0, 2-1, 0-0, 1-1, 2-0, and so on, and the highest-probability scoreline is the pick. The implied edge column is the difference between that probability and bet365’s price on the same scoreline. Where the model and the market agree, the edge is near zero, and the rationale flags the pick as market-aligned. Where they diverge, the edge is positive, and the rationale walks the reader through which features pulled the model away from the price.<\/p>\n\n\n\n

The weights are not fixed forever. After Matchday 1 of the tournament, the system starts giving more weight to actual in-tournament performance (shot quality at this World Cup, not last summer’s friendlies) and the qualifying prior fades. By the knockout rounds, the prior is doing very little of the lifting and the recent-match data is doing most of it.<\/p>\n\n\n\n

How we measure the AI Predictor<\/h2>\n\n\n\n

A predictor that does not track its own performance is not a predictor; it is marketing. The running record above the picks on the hub page is the system’s report card, and it updates after every final whistle.<\/p>\n\n\n\n

Three numbers matter.<\/p>\n\n\n\n

Result hits.<\/strong> Did the Predictor call the correct outcome, whether home win, draw, or away win? This is the loosest measure but the most directly translatable to a 1X2 betting outcome.<\/p>\n\n\n\n

Exact-score hits.<\/strong> Did the Predictor call the exact scoreline? Correct-score betting is notoriously hard. Top tipsters typically hit fewer than 10 per cent of their exact-score calls, and any system claiming a sustainable edge on this market should be regarded with deep suspicion. We expect the Predictor’s exact-score hit rate to land in the 8 to 12 per cent band over a 64-match tournament. Higher than that means the model is calibrating well; lower means it is not.<\/p>\n\n\n\n

Units returned against bet365’s closing line.<\/strong> Every pick is logged at the bet365 closing price on the predicted scoreline. After the result lands, the unit return is calculated and added to the running ledger. Over a tournament this number tells you whether the Predictor’s edge is real or whether it is noise dressed up as edge.<\/p>\n\n\n\n

After the tournament we will publish a full calibration plot: predicted probabilities versus realised frequencies, plotted across all 64 matches. If the line falls on the diagonal, the model’s confidence is honest. If it drifts above, the model is overclaiming. If it drifts below, it is underclaiming. That plot is the single most honest piece of writing we will publish about the Predictor.<\/p>\n\n\n\n

What the AI Predictor does not do<\/h2>\n\n\n\n

Five things, named clearly.<\/p>\n\n\n\n

It does not know about injuries or suspensions.<\/strong> The model picks the score from data already on the field, including recent-form numbers, market price, and qualifying record. It does not have a real-time feed from the medical room. If a key forward picks up a knock the night before a group game, the model will still be working from the form data that includes that player. Pair the Predictor with the team-news section of the relevant match preview before acting on a pick.<\/p>\n\n\n\n

It does not model tactical surprises.<\/strong> A side that ran 4-3-3 through qualifying but switches to a 5-4-1 low block against a stronger opponent will not be caught by the model until that pattern repeats in tournament data. Knockout-round tactical changes are exactly the kind of edge case where the data lags behind the soccer.<\/p>\n\n\n\n

It is not a substitute for the match preview.<\/strong> The card row on the hub gives you a pick, a price, and an edge. The full preview gives you team news, tactical context, predicted lineups, set-piece angles, and prop-bet thinking. Use the Predictor alongside the preview, not instead of it.<\/p>\n\n\n\n\n

Coverage of recent-form data varies by region.<\/strong> Where our data feed has current matches for a side, the model uses it. UEFA, CONMEBOL, AFC and CAF nations are well-covered via their respective qualifying tournaments and AFCON 2025. CONCACAF national teams (Mexico, USA, Canada, Haiti, Curacao, Panama) are not currently covered for the 2024 to 2026 window, so the model leans on the market prior and the historical strength baseline for those sides, and the per-match rationale flags the asymmetry. The hub article tells you when a pick is data-rich and when it is market-led.<\/p>\n\n\n\n\n

It is not a guarantee.<\/strong> Sixty-four matches at a World Cup will include results no model, and no tipster, saw coming. That is soccer. The Predictor’s job is to be honest about its inputs and accountable for its outputs. It is not to guarantee a winner.<\/p>\n\n\n\n

Track record<\/h2>\n\n\n\n

This section becomes real after Matchday 1 of the 2026 World Cup. From the opening fixture in Mexico City onwards, the running record on the hub page<\/a> tracks the Predictor’s calls in real time.<\/p>\n\n\n\n

After the tournament, we will add to this section: a calibration plot, a breakdown by group versus knockout-round performance, and a head-to-head against bet365’s closing line. The first instalment of that retrospective lands within a week of the final.<\/p>\n\n\n\n

Subsequent tournaments and competitions, including MLS, the Premier League, Liga MX, and the Champions League, get added below as the Predictor rolls out beyond the World Cup. Each gets its own ledger. The cumulative picture across competitions sits at the top of this section.<\/p>\n\n\n\n

A closing word<\/h2>\n\n\n\n

The Predictor will be wrong. Often, in fact, because exact-score betting punishes anyone claiming to be right. What it will not be is opaque, unaccountable, or hyped beyond what the data supports. Read the picks against this page, hold the running record to a standard, and judge the system across the 64 matches rather than the next one. That is the only honest way to use a predictor.<\/p>\n\n\n\n

21+ | Gambling Problem? Call 1-800-GAMBLER | Odds approximate at time of writing<\/em><\/p>\n\n","protected":false},"excerpt":{"rendered":"

This page sets out the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it deliberately does not try to do. It is a transparent system, not a black box. The Predictor puts a predicted scoreline alongside bet365’s price for every match at the 2026…<\/p>\n","protected":false},"author":393,"featured_media":8944,"parent":0,"menu_order":0,"template":"","meta":{"_acf_changed":false,"_yoast_wpseo_focuskw":"ai predictor methodology","_yoast_wpseo_title":"AI Predictor Methodology: How Our Score Picks Work | Squawka","_yoast_wpseo_metadesc":"An honest explainer of the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it does not try to do.","footnotes":""},"tags":[272,273],"news-category":[],"class_list":["post-8935","news","type-news","status-publish","has-post-thumbnail","hentry","tag-prediction-markets","tag-world-cup-2026"],"acf":{"external_featured_image_url":"","hide_featured_image_pattern":true},"yoast_head":"\nAI Predictor Methodology: How Our Score Picks Work | Squawka<\/title>\n<meta name=\"description\" content=\"An honest explainer of the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it does not try to do.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI Predictor Methodology: How Our Score Picks Work\" \/>\n<meta property=\"og:description\" content=\"An honest explainer of the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it does not try to do.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/\" \/>\n<meta property=\"og:site_name\" content=\"Squawka | US\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/SquawkaFootballNews\/\" \/>\n<meta property=\"article:modified_time\" content=\"2026-06-05T23:14:26+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/06\/05084334\/ai-predictor-methodology-1920x1080-1.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1920\" \/>\n\t<meta property=\"og:image:height\" content=\"1080\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@Squawka\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/\",\"url\":\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/\",\"name\":\"AI Predictor Methodology: How Our Score Picks Work | Squawka\",\"isPartOf\":{\"@id\":\"https:\/\/www.squawka.com\/us\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/06\/05084334\/ai-predictor-methodology-1920x1080-1.jpg\",\"datePublished\":\"2026-06-05T22:35:59+00:00\",\"dateModified\":\"2026-06-05T23:14:26+00:00\",\"description\":\"An honest explainer of the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it does not try to do.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#primaryimage\",\"url\":\"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/06\/05084334\/ai-predictor-methodology-1920x1080-1.jpg\",\"contentUrl\":\"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/06\/05084334\/ai-predictor-methodology-1920x1080-1.jpg\",\"width\":1920,\"height\":1080,\"caption\":\"Inside the Squawka AI Predictor methodology: what it weighs, how it picks a scoreline, how we measure it.\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.squawka.com\/us\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"News\",\"item\":\"https:\/\/www.squawka.com\/us\/news\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"AI Predictor Methodology: How Our Score Picks Work\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.squawka.com\/us\/#website\",\"url\":\"https:\/\/www.squawka.com\/us\/\",\"name\":\"Squawka US\",\"description\":\"Soccer News and Predictions | Stats, Betting\",\"publisher\":{\"@id\":\"https:\/\/www.squawka.com\/us\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.squawka.com\/us\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.squawka.com\/us\/#organization\",\"name\":\"Squawka US\",\"url\":\"https:\/\/www.squawka.com\/us\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.squawka.com\/us\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/04\/23072352\/Squawka-Logo.jpg\",\"contentUrl\":\"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/04\/23072352\/Squawka-Logo.jpg\",\"width\":1000,\"height\":1000,\"caption\":\"Squawka US\"},\"image\":{\"@id\":\"https:\/\/www.squawka.com\/us\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/SquawkaFootballNews\/\",\"https:\/\/x.com\/Squawka\",\"https:\/\/www.instagram.com\/squawkafootball\/\"],\"description\":\"Squawka is a football editorial site covering the Premier League, Champions League, MLS, Liga MX, FIFA World Cup 2026 and the wider international game. We publish match previews, tactical analysis, player and team stats, outright odds, betting tips, streaming guides and long-form features for a committed football audience. Founded in the UK and part of OneTwenty Group, Squawka now runs localised editions for the UK (squawka.com\/en\/), United States (squawka.com\/us\/), Mexican-Spanish (squawka.com\/us-es\/), Ireland, Netherlands, Nigeria, Kenya, Uganda, South Africa and Ghana. Each edition is editorially tailored to its market, with locale-specific competition focus, operator compliance and commercial partnerships. Traffic skews toward high-intent football readers \u2014 supporters researching fixtures, form, odds and where to watch \u2014 making Squawka a strong fit for sportsbook, prediction-market, DFS, streaming and sports-merchandise brands across the UK, Europe and North America.\",\"foundingDate\":\"2012-06-11\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"AI Predictor Methodology: How Our Score Picks Work | Squawka","description":"An honest explainer of the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it does not try to do.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/","og_locale":"en_US","og_type":"article","og_title":"AI Predictor Methodology: How Our Score Picks Work","og_description":"An honest explainer of the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it does not try to do.","og_url":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/","og_site_name":"Squawka | US","article_publisher":"https:\/\/www.facebook.com\/SquawkaFootballNews\/","article_modified_time":"2026-06-05T23:14:26+00:00","og_image":[{"width":1920,"height":1080,"url":"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/06\/05084334\/ai-predictor-methodology-1920x1080-1.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_site":"@Squawka","twitter_misc":{"Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/","url":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/","name":"AI Predictor Methodology: How Our Score Picks Work | Squawka","isPartOf":{"@id":"https:\/\/www.squawka.com\/us\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#primaryimage"},"image":{"@id":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#primaryimage"},"thumbnailUrl":"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/06\/05084334\/ai-predictor-methodology-1920x1080-1.jpg","datePublished":"2026-06-05T22:35:59+00:00","dateModified":"2026-06-05T23:14:26+00:00","description":"An honest explainer of the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it does not try to do.","breadcrumb":{"@id":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#primaryimage","url":"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/06\/05084334\/ai-predictor-methodology-1920x1080-1.jpg","contentUrl":"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/06\/05084334\/ai-predictor-methodology-1920x1080-1.jpg","width":1920,"height":1080,"caption":"Inside the Squawka AI Predictor methodology: what it weighs, how it picks a scoreline, how we measure it."},{"@type":"BreadcrumbList","@id":"https:\/\/www.squawka.com\/us\/news\/squawkas-ai-predictor-methodology\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.squawka.com\/us\/"},{"@type":"ListItem","position":2,"name":"News","item":"https:\/\/www.squawka.com\/us\/news\/"},{"@type":"ListItem","position":3,"name":"AI Predictor Methodology: How Our Score Picks Work"}]},{"@type":"WebSite","@id":"https:\/\/www.squawka.com\/us\/#website","url":"https:\/\/www.squawka.com\/us\/","name":"Squawka US","description":"Soccer News and Predictions | Stats, Betting","publisher":{"@id":"https:\/\/www.squawka.com\/us\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.squawka.com\/us\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.squawka.com\/us\/#organization","name":"Squawka US","url":"https:\/\/www.squawka.com\/us\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.squawka.com\/us\/#\/schema\/logo\/image\/","url":"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/04\/23072352\/Squawka-Logo.jpg","contentUrl":"https:\/\/media.squawka.com\/images\/sites\/13\/2026\/04\/23072352\/Squawka-Logo.jpg","width":1000,"height":1000,"caption":"Squawka US"},"image":{"@id":"https:\/\/www.squawka.com\/us\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/SquawkaFootballNews\/","https:\/\/x.com\/Squawka","https:\/\/www.instagram.com\/squawkafootball\/"],"description":"Squawka is a football editorial site covering the Premier League, Champions League, MLS, Liga MX, FIFA World Cup 2026 and the wider international game. We publish match previews, tactical analysis, player and team stats, outright odds, betting tips, streaming guides and long-form features for a committed football audience. Founded in the UK and part of OneTwenty Group, Squawka now runs localised editions for the UK (squawka.com\/en\/), United States (squawka.com\/us\/), Mexican-Spanish (squawka.com\/us-es\/), Ireland, Netherlands, Nigeria, Kenya, Uganda, South Africa and Ghana. Each edition is editorially tailored to its market, with locale-specific competition focus, operator compliance and commercial partnerships. Traffic skews toward high-intent football readers \u2014 supporters researching fixtures, form, odds and where to watch \u2014 making Squawka a strong fit for sportsbook, prediction-market, DFS, streaming and sports-merchandise brands across the UK, Europe and North America.","foundingDate":"2012-06-11"}]}},"yoast_title":"AI Predictor Methodology: How Our Score Picks Work | Squawka","yoast_description":"An honest explainer of the Squawka AI Predictor methodology: what it weighs, how it picks a correct score, how we measure it, and what it does not try to do.","yoast_keyword":"ai predictor methodology","_links":{"self":[{"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/news\/8935","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/news"}],"about":[{"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/types\/news"}],"author":[{"embeddable":true,"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/users\/393"}],"version-history":[{"count":4,"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/news\/8935\/revisions"}],"predecessor-version":[{"id":8998,"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/news\/8935\/revisions\/8998"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/media\/8944"}],"wp:attachment":[{"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/media?parent=8935"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/tags?post=8935"},{"taxonomy":"news-category","embeddable":true,"href":"https:\/\/www.squawka.com\/us\/wp-json\/wp\/v2\/news-category?post=8935"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}