--- title: Issue #136 - Causal Inference: Why Your Model Cannot... description: Classical ML models answer predictive questions but fail at causal ones — they cannot reliably estimate what will happen if you intervene. This piece... canonical: https://daily.dev/posts/issue-136---causal-inference-why-your-model-cannot-answer-what-if--d8uzbn6ey twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Issue #136 - Causal Inference: Why Your Model Cannot Answer "What If"? | daily.dev og:description: Classical ML models answer predictive questions but fail at causal ones — they cannot reliably estimate what will happen if you intervene. This piece... og:url: https://daily.dev/posts/issue-136---causal-inference-why-your-model-cannot-answer-what-if--d8uzbn6ey og:image: https://api.daily.dev/og/posts/D8uzBN6eY.png og:image:alt: Issue #136 - Causal Inference: Why Your Model Cannot Answer "What If"? og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Issue #136 - Causal Inference: Why Your Model Cannot Answer "What If"? **[Machine Learning Pills](https://daily.dev/sources/mlpills)** · 12 min read · 0 upvotes · 0 comments ## Summary Classical ML models answer predictive questions but fail at causal ones — they cannot reliably estimate what will happen if you intervene. This piece introduces causal inference as a distinct discipline, explaining the fundamental problem (counterfactuals are unobservable), the potential outcomes framework (ATE, ATT, CATE), and the three key assumptions (ignorability, positivity, SUTVA). It also covers Structural Causal Models and DAGs from Judea Pearl's work, explaining confounders, mediators, and colliders, and why 'controlling for everything' can introduce rather than remove bias. The post is Part 1 of a three-part series; Parts 2 and 3 will cover classical methodologies and ML-based causal methods respectively. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the difference between a predictive model and a causal inference model? A predictive model estimates what is likely to happen given observed patterns, such as who is likely to churn or default, while a causal model estimates what will happen if you intervene, such as whether a retention offer actually prevents churn. Predictive models can conflate the effect of an action with selection effects, since treatment assignment (who gets a drug, an ad, or an offer) is rarely random, entangling correlation with true causation. _Anyone deciding whether a model can justify an intervention can dig deeper into causal inference concepts on daily.dev._ ### What is the fundamental problem of causal inference? For any single unit, only one of the two potential outcomes can ever be observed: the outcome under treatment, Y(1), or the outcome without treatment, Y(0), never both for the same unit at the same time. The missing outcome is called the counterfactual, and it is unobservable by nature rather than due to poor data collection, making causal inference fundamentally a missing-data problem that every estimation method tries to address. _Data scientists studying counterfactual reasoning can track deeper causal methods content on daily.dev._ ### What is the difference between ATE, ATT, and CATE in causal inference? ATE (average treatment effect) is the average causal effect across the entire population, ATT (average treatment effect on the treated) is the effect specifically among units that received treatment, and CATE (conditional average treatment effect) is the treatment effect for a subgroup defined by specific features, such as age or user type. CATE underlies personalization and uplift modeling, since it reveals which subgroups respond most to an intervention. _Practitioners choosing the right treatment-effect estimand can follow more causal inference breakdowns on daily.dev._ ## Similar posts on daily.dev - [Causal ML for the Aspiring Data Scientist](https://daily.dev/posts/causal-ml-for-the-aspiring-data-scientist-xj4ey04uc) · Towards Data Science · 1 upvotes · 0 comments - [From Prediction to Intervention](https://daily.dev/posts/from-prediction-to-intervention-n2aqewbwf) · Medium · 0 upvotes · 0 comments - [Causal Inference Is Eating Machine Learning](https://daily.dev/posts/causal-inference-is-eating-machine-learning-ajbqw0k9p) · Towards Data Science · 0 upvotes · 0 comments - [Issue \#138 - From Average Effects to Personalised Decisions](https://daily.dev/posts/issue-138---from-average-effects-to-personalised-decisions-g7rpxqyvk) · Machine Learning Pills · 1 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#data-science](https://daily.dev/tags/data-science) [View this post on daily.dev](https://daily.dev/posts/issue-136---causal-inference-why-your-model-cannot-answer-what-if--d8uzbn6ey) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Issue #136 - Causal Inference: Why Your Model Cannot Answer \"What If\"?","url":"https://daily.dev/posts/issue-136---causal-inference-why-your-model-cannot-answer-what-if--d8uzbn6ey","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/issue-136---causal-inference-why-your-model-cannot-answer-what-if--d8uzbn6ey"},"datePublished":"2026-07-14T15:51:47.393Z","dateModified":"2026-09-13T20:53:14.586Z","description":"Classical ML models answer predictive questions but fail at causal ones — they cannot reliably estimate what will happen if you intervene. This piece...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3cdc8ce60c0b9d5e1f4df5b9413d90da?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3cdc8ce60c0b9d5e1f4df5b9413d90da?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Machine Learning Pills","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Machine Learning Pills","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/4a65b589ef234a99a2fbc0c4cf043d7f","url":"https://daily.dev/sources/mlpills"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/issue-136---causal-inference-why-your-model-cannot-answer-what-if--d8uzbn6ey","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,data-science","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Machine Learning Pills","item":"https://daily.dev/sources/mlpills"},{"@type":"ListItem","position":3,"name":"Issue #136 - Causal Inference: Why Your Model Cannot Answer \"What If\"?"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/issue-136---causal-inference-why-your-model-cannot-answer-what-if--d8uzbn6ey#faq","mainEntity":[{"@type":"Question","name":"What is the difference between a predictive model and a causal inference model?","acceptedAnswer":{"@type":"Answer","text":"A predictive model estimates what is likely to happen given observed patterns, such as who is likely to churn or default, while a causal model estimates what will happen if you intervene, such as whether a retention offer actually prevents churn. Predictive models can conflate the effect of an action with selection effects, since treatment assignment (who gets a drug, an ad, or an offer) is rarely random, entangling correlation with true causation. Anyone deciding whether a model can justify an intervention can dig deeper into causal inference concepts on daily.dev."}},{"@type":"Question","name":"What is the fundamental problem of causal inference?","acceptedAnswer":{"@type":"Answer","text":"For any single unit, only one of the two potential outcomes can ever be observed: the outcome under treatment, Y(1), or the outcome without treatment, Y(0), never both for the same unit at the same time. The missing outcome is called the counterfactual, and it is unobservable by nature rather than due to poor data collection, making causal inference fundamentally a missing-data problem that every estimation method tries to address. Data scientists studying counterfactual reasoning can track deeper causal methods content on daily.dev."}},{"@type":"Question","name":"What is the difference between ATE, ATT, and CATE in causal inference?","acceptedAnswer":{"@type":"Answer","text":"ATE (average treatment effect) is the average causal effect across the entire population, ATT (average treatment effect on the treated) is the effect specifically among units that received treatment, and CATE (conditional average treatment effect) is the treatment effect for a subgroup defined by specific features, such as age or user type. CATE underlies personalization and uplift modeling, since it reveals which subgroups respond most to an intervention. Practitioners choosing the right treatment-effect estimand can follow more causal inference breakdowns on daily.dev."}}]} ```