--- title: Budget Allocation at Scale: Building an ML Optimization... description: Atlassian's performance marketing team built a two-stage ML system to optimize paid advertising budget allocation at scale. The system uses a LightGBM-based... canonical: https://daily.dev/posts/budget-allocation-at-scale-building-an-ml-optimization-system-for-paid-marketing-avblznziq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Budget Allocation at Scale: Building an ML Optimization System for Paid Marketing | daily.dev og:description: Atlassian's performance marketing team built a two-stage ML system to optimize paid advertising budget allocation at scale. The system uses a LightGBM-based... og:url: https://daily.dev/posts/budget-allocation-at-scale-building-an-ml-optimization-system-for-paid-marketing-avblznziq og:image: https://api.daily.dev/og/posts/avbLZnziq.png og:image:alt: Budget Allocation at Scale: Building an ML Optimization System for Paid Marketing 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. # Budget Allocation at Scale: Building an ML Optimization System for Paid Marketing **[Atlassian](https://daily.dev/sources/atlassian)** · 8 min read · 0 upvotes · 0 comments ## Summary Atlassian's performance marketing team built a two-stage ML system to optimize paid advertising budget allocation at scale. The system uses a LightGBM-based payout model to predict business outcomes as a function of spend (capturing diminishing returns), paired with a Bayesian Optimization-based budget optimizer that allocates a fixed total budget across hundreds of channels, markets, and products to maximize ROI under real-world constraints. A Cross-Entropy method serves as an independent validator. Online experiments using a pre-and-post design across 3 marketing channels and 2 products showed a double-digit percent reduction in cost per business metric at equivalent spend levels, with no budget increase required. Future work includes better extrapolation handling with hybrid tree-parametric models, uncertainty-aware exploration-exploitation, and richer lag and interaction features. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How Yelp Built a Back-Testing Engine for Safer, Smarter Ad Budget Allocation](https://daily.dev/posts/how-yelp-built-a-back-testing-engine-for-safer-smarter-ad-budget-allocation-v8cgpjvzn) · Yelp Engineering · 0 upvotes · 0 comments - [Scaling Reliable Experimentation in a Two-Sided AdTech Marketplace: ZMS Budget Split](https://daily.dev/posts/scaling-reliable-experimentation-in-a-two-sided-adtech-marketplace-zms-budget-split-segb1krmo) · Zalando · 0 upvotes · 0 comments - [Medium](https://daily.dev/posts/medium-megr8nsrt) · Medium · 0 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/budget-allocation-at-scale-building-an-ml-optimization-system-for-paid-marketing-avblznziq) ```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":"Budget Allocation at Scale: Building an ML Optimization System for Paid Marketing","url":"https://daily.dev/posts/budget-allocation-at-scale-building-an-ml-optimization-system-for-paid-marketing-avblznziq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/budget-allocation-at-scale-building-an-ml-optimization-system-for-paid-marketing-avblznziq"},"datePublished":"2026-07-30T05:06:48.682Z","dateModified":"2026-07-30T05:10:50.859Z","description":"Atlassian's performance marketing team built a two-stage ML system to optimize paid advertising budget allocation at scale. The system uses a LightGBM-based...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4e96aa8f331fea437401f64f530ce810?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4e96aa8f331fea437401f64f530ce810?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Atlassian","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":"Atlassian","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/44750d8e66de4411bb477159b321bb43","url":"https://daily.dev/sources/atlassian"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/budget-allocation-at-scale-building-an-ml-optimization-system-for-paid-marketing-avblznziq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,data-science","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Atlassian","item":"https://daily.dev/sources/atlassian"},{"@type":"ListItem","position":3,"name":"Budget Allocation at Scale: Building an ML Optimization System for Paid Marketing"}]} ```