[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"cms-page:\u002Fblog\u002Fmeridian-googles-marketing-mix-modelling":3},{"date":4,"date_gmt":4,"content":5,"sticky":7,"format":8,"categories":9,"collections":12,"coauthors":13,"class_list":15,"acf":25,"head_links":453,"breadcrumbs":454,"reading_minutes":147,"category":462,"head":465},"2025-04-16T15:37:05",{"rendered":6},"\n\u003Cp>Ever since Google announced that it would be releasing an open-source Media Mix Modelling (MMM) package, which adds to and improves upon its predecessor, LightweightMMM, data scientists and marketers have been eagerly waiting for access to the platform. Most were left waiting until \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fblog.google\u002Fproducts\u002Fads-commerce\u002Fmeridian-marketing-mix-model-open-to-everyone\u002F\">Google announced\u003C\u002Fa> they would release it to the world on the 29th of January 2025.\u003C\u002Fp>\n\n\n\n\u003Chr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\"\u002F>\n\n\n\n\u003Cdiv class=\"table-of-contents\">\u003Cul>\u003Cli class=\"heading-h2\">\u003Ca href=\"#what-did-we-already-know\">What did we already know?\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"heading-h2\">\u003Ca href=\"#what-google-meridian-gets-right\">What Google Meridian gets right\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"heading-h3\">\u003Ca href=\"#a-fully-functional-bayesian-mmm-model\">A fully functional Bayesian MMM Model\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"heading-h3\">\u003Ca href=\"#built-in-priors-reduce-the-learning-curve\">Built-in priors reduce the learning curve\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"heading-h3\">\u003Ca href=\"#effective-visual-reporting\">Effective visual reporting\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"heading-h2\">\u003Ca href=\"#what-meridian-could-improve\">What Meridian could improve\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"heading-h3\">\u003Ca href=\"#meridian-lacks-flexibility-for-advanced-users\">Meridian lacks flexibility for advanced users\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"heading-h3\">\u003Ca href=\"#marketing-mix-modelling-will-always-require-expertise\">Marketing Mix Modelling will always require expertise\u003C\u002Fa>\u003C\u002Fli>\u003C\u002Ful>\u003C\u002Fdiv>\n\n\n\n\u003Chr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\"\u002F>\n\n\n\n\u003Ch2 class=\"wp-block-heading\" id=\"what-did-we-already-know\">\u003Cstrong>What did we already know?\u003C\u002Fstrong>\u003C\u002Fh2>\n\n\n\n\u003Cp>In January, just before the spontaneous release of Google Meridian, \u003Ca rel=\"noreferrer noopener\" href=\"\u002Fblog\u002Fgoogle-meridian-what-you-need-to-know\u002F\">we published a blog\u003C\u002Fa> outlining everything Meridian. Our conclusion at the time was that, while Meridian provides a platform built on similar foundations to current MMM tools, it lacked the flexibility we needed at Impression. Based on what we knew then, we felt Meridian didn’t support features like channel hierarchical modelling and time-variant media channels, which we could implement using \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.pymc.io\u002Fwelcome.html\">PyMC\u003C\u002Fa>. The ability to customise models fully, in our opinion, is vital in building an MMM, because every business is different. Despite this, we must constantly try to improve our services, and if Meridian is the answer to that, we would be missing an opportunity if we dismissed it before it is even released!&nbsp;\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\" id=\"what-google-meridian-gets-right\">\u003Cstrong>What Google Meridian gets right\u003C\u002Fstrong>\u003C\u002Fh2>\n\n\n\n\u003Ch3 class=\"wp-block-heading\" id=\"a-fully-functional-bayesian-mmm-model\">A fully functional Bayesian MMM Model\u003C\u002Fh3>\n\n\n\n\u003Cp>\u003Cstrong>Out of the box, Meridian includes:\u003C\u002Fstrong>\u003C\u002Fp>\n\n\n\n\u003Cul class=\"wp-block-list\">\n\u003Cli>\u003Ca rel=\"noreferrer noopener\" href=\"\u002Fblog\u002Fbayesian-statistics-in-media-mix-modelling-a-real-world-analogy\u002F\">Bayesian\u003C\u002Fa> inference for uncertainty estimation.\u003C\u002Fli>\n\n\n\n\u003Cli>Adstock transformation to model carryover effects.\u003C\u002Fli>\n\n\n\n\u003Cli>Saturation functions to capture diminishing returns.\u003C\u002Fli>\n\n\n\n\u003Cli>Hierarchical geo-modelling, which is useful for regional insights.\u003C\u002Fli>\n\u003C\u002Ful>\n\n\n\n\u003Cp>It’s a solid implementation of modern MMM best practices.\u003C\u002Fp>\n\n\n\n\u003Ch3 class=\"wp-block-heading\" id=\"built-in-priors-reduce-the-learning-curve\">Built-in priors reduce the learning curve\u003C\u002Fh3>\n\n\n\n\u003Cp>One advantage of Meridian is that Google has pre-configured priors and hyperparameters, parameters that control the learning process of a model, based on industry knowledge. This means you don’t have to spend as much time tuning the model, which is a plus if you’re not familiar with Bayesian statistics.&nbsp;\u003C\u002Fp>\n\n\n\n\u003Ch3 class=\"wp-block-heading\" id=\"effective-visual-reporting\">Effective visual reporting\u003C\u002Fh3>\n\n\n\n\u003Cp>After running your MMM, Meridian has the option to output all of your data into a two-page HTML report. In my opinion, this report is an excellent way to present your model outputs, offering immediate insights into channel performance and ROI. The waterfall chart (see below) effectively breaks down sales contributions, while the response curves provide a visual understanding of saturation points and diminishing returns for each paid media channel. This allows for \u003Ca rel=\"noreferrer noopener\" href=\"\u002Fblog\u002Fgranularity-marketing-mix-modelling\u002F\">quick identification of high-performing areas\u003C\u002Fa> and potential optimisation opportunities.\u003C\u002Fp>\n\n\n\u003Cdiv class=\"wp-block-image\">\n\u003Cfigure class=\"aligncenter size-full\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"665\" height=\"386\" src=\"https:\u002F\u002Fimages.impression.co.uk\u002F2025\u002F04\u002Fcontribution-by-baseline-and-marketing-channels.png?auto=compress%2Cformat&q=90\" alt=\"\" class=\"wp-image-32923\"\u002F>\u003Cfigcaption class=\"wp-element-caption\">Source: \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fdevelopers.google.com\u002Fmeridian\u002Fnotebook\u002Fmeridian-getting-started\">Getting Started: Google Meridian\u003C\u002Fa>\u003C\u002Ffigcaption>\u003C\u002Ffigure>\u003C\u002Fdiv>\n\n\n\u003Cp>\u003Cstrong>But here’s the problem\u003C\u002Fstrong>: MMM is not a one-size-fits-all problem. And that’s exactly where Meridian falls short.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\" id=\"what-meridian-could-improve\">\u003Cstrong>What Meridian could improve\u003C\u002Fstrong>\u003C\u002Fh2>\n\n\n\n\u003Ch3 class=\"wp-block-heading\" id=\"meridian-lacks-flexibility-for-advanced-users\">Meridian lacks flexibility for advanced users\u003C\u002Fh3>\n\n\n\n\u003Cp>Meridian provides a solid foundation for Marketing Mix Modelling, but it does have some limitations when it comes to customisation, especially from the perspective of marketing data scientists.\u003C\u002Fp>\n\n\n\n\u003Cp>If you need to use different adstock or saturation functions, you’re \u003Ca rel=\"noreferrer noopener\" href=\"\u002Fblog\u002Fquestions-to-ask-marketing-mix-modelling-vendors\u002F\">limited to what Meridian offers\u003C\u002Fa>. Custom likelihood functions aren’t easily adjustable, and if your business has unique constraints, making the necessary changes could be a challenge.\u003C\u002Fp>\n\n\n\n\u003Cp>\u003Ca rel=\"noreferrer noopener\" href=\"\u002Fblog\u002Fnavigating-mmm\u002F\">MMM isn’t a one-size-fits-all approach\u003C\u002Fa>. Different industries, marketing channels, and regions require different modelling choices, and Meridian’s structured framework might not work for everyone. For example, the figure below shows the built-in adstock effect (in blue), but Meridian doesn’t support the delayed adstock effect (in orange), which is useful for businesses with longer customer decision cycles, like buying a car or planning a wedding.\u003C\u002Fp>\n\n\n\u003Cdiv class=\"wp-block-image\">\n\u003Cfigure class=\"aligncenter size-full\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"846\" height=\"393\" src=\"https:\u002F\u002Fimages.impression.co.uk\u002F2025\u002F04\u002Fgeometric-adstock-vs-delayed-adstock.png?auto=compress%2Cformat&q=90\" alt=\"\" class=\"wp-image-32924\"\u002F>\u003C\u002Ffigure>\u003C\u002Fdiv>\n\n\n\u003Ch3 class=\"wp-block-heading\" id=\"marketing-mix-modelling-will-always-require-expertise\">Marketing Mix Modelling will always require expertise\u003C\u002Fh3>\n\n\n\n\u003Cp>One of Google’s main selling points is that Meridian makes MMM more accessible. But the reality is:\u003C\u002Fp>\n\n\n\n\u003Cul class=\"wp-block-list\">\n\u003Cli>Model \u003Ca rel=\"noreferrer noopener\" href=\"\u002Fblog\u002Fdata-requirements-for-marketing-mix-modelling\u002F\">selection and validation\u003C\u002Fa> require deep statistical expertise. Even with built-in priors, interpreting results and making adjustments still require knowledge of Bayesian statistics.\u003C\u002Fli>\n\n\n\n\u003Cli>Business context cannot be automated. A pre-built model, no matter how well-designed, will never fully capture the nuances of every business&#8217;s marketing reality.\u003C\u002Fli>\n\n\n\n\u003Cli>Debugging Bayesian models is not always easy. Even in structured frameworks like Meridian, properly diagnosing model fit issues or adjusting priors requires technical skill.\u003C\u002Fli>\n\u003C\u002Ful>\n\n\n\n\u003Cp>So, who is Meridian really for? If a company has the expertise to run MMM at a high level, it may still prefer a more flexible, customisable solution. But for businesses looking for an easier entry point into MMM, Meridian provides a structured approach with industry best practices.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image size-full\">\u003Ca rel=\"noreferrer noopener\" href=\"\u002Fmedia-solutions\u002Fmeasurement\u002F\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"3840\" height=\"540\" src=\"https:\u002F\u002Fimages.impression.co.uk\u002F2024\u002F04\u002Ff0sKYLsk-Measurement_Banner_01.jpg?auto=compress%2Cformat&q=90\" alt=\"\" class=\"wp-image-27925\"\u002F>\u003C\u002Fa>\u003C\u002Ffigure>\n\n\n\n\u003Cp>At its core, MMM is not a problem that can be fully automated. Every business has unique challenges, and pre-built solutions like \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fdevelopers.google.com\u002Fmeridian\">Meridian\u003C\u002Fa> and \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Ffacebookexperimental.github.io\u002FRobyn\u002F\">Robyn\u003C\u002Fa>, Meta&#8217;s open-source MMM, will always have some limitations.\u003C\u002Fp>\n\n\n\n\u003Cp>For teams that prioritise full control, customisation, and advanced modelling techniques, PyMC remains our preferred choice. It allows for:\u003C\u002Fp>\n\n\n\n\u003Cul class=\"wp-block-list\">\n\u003Cli>Defining custom priors, likelihoods, and transformations based on business needs.\u003C\u002Fli>\n\n\n\n\u003Cli>Adapting the model for any industry, geography, or business constraint.\u003C\u002Fli>\n\n\n\n\u003Cli>Scaling efficiently with modern Bayesian inference techniques.\u003C\u002Fli>\n\u003C\u002Ful>\n\n\n\n\u003Cp>However, for teams that want a more standardised approach with less manual tuning, Meridian offers practical alternatives. The key is understanding your business needs and selecting the right tool accordingly.\u003C\u002Fp>\n\n\n\n\u003Cp>At the end of the day, \u003Ca rel=\"noreferrer noopener\" href=\"\u002Fblog\u002Fmedia-mix-modelling\u002F\">Marketing Mix Modelling is about understanding marketing effectiveness\u003C\u002Fa> at a deep level, and that requires careful model selection, validation, and interpretation, regardless of the platform used.\u003C\u002Fp>\n",false,"standard",[10,11],280,41,[],[14],120,[16,17,18,19,20,21,22,23,24],"post-32917","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-engineering","category-measurement",{"page_content_modules":26,"hero":181},[27,135],{"acf_fc_layout":28,"reduced":29,"top_overlap":-1,"bottom_underlap":-1,"disable_observer":29,"title":30,"content":6,"authors":31},"blog_post_content",true,"Meridian: Google’s Answer to Marketing Mix Modelling",[32],{"id":33,"path":34,"display_name":35,"job_title":36,"description":37,"avatar_url":38,"acf":39},29,"\u002Fabout\u002Four-team\u002Fharry-brace\u002F","Harry Brace","Director, Head of Solutions","I'm the Director, Head of Solutions at Impression. I spend my time debugging and implementing tracking using Google Tag Manager, managing data warehousing platforms and building Looker Studio reports!","https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress&fit=crop&fm=jpg&h=150&q=80&w=150&bg=CFE6F9",{"full_bio":40,"job_title":36,"specialist_service_links":41,"photo":79},"\u003Cp>Director, Head of Solutions. Joined Impression in November 2017.\u003C\u002Fp>\n\u003Cp>I gained 4 years of experience as a web developer before moving to Impression as a digital account manager in 2017. I moved across to the Analytics department in 2019 and I’ve been strengthening and growing our Analytics offering ever since.\u003C\u002Fp>\n\u003Cp>Day to day, I spend my time debugging and implementing tracking using Google Tag Manager, managing data warehousing platforms and building Looker Studio reports!\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Something that I’m proud of:\u003C\u002Fstrong>\u003Cbr \u002F>\nBuilding the analytics department over the last couple of years with the help of Aaron and now Alex H.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Outside of work:\u003C\u002Fstrong>\u003Cbr \u002F>\nFind me socialising, skiing or gaming.\u003C\u002Fp>\n",[42,60,70],{"page":43,"link_text":59},{"ID":44,"post_author":45,"post_date":46,"post_date_gmt":46,"post_content":47,"post_title":48,"post_excerpt":47,"post_status":49,"comment_status":50,"ping_status":50,"post_password":47,"post_name":51,"to_ping":47,"pinged":47,"post_modified":52,"post_modified_gmt":52,"post_content_filtered":47,"post_parent":53,"guid":54,"menu_order":53,"post_type":55,"post_mime_type":47,"comment_count":56,"filter":57,"url_path":58},374,"98","2021-01-11 16:25:32","","Analytics","publish","closed","analytics","2026-09-28 11:36:16",0,"\u002F?page_id=374","page","0","raw","\u002Fanalytics\u002F","Web Analytics",{"page":61,"link_text":64},{"ID":62,"post_author":45,"post_date":63,"post_date_gmt":63,"post_content":47,"post_title":64,"post_excerpt":47,"post_status":49,"comment_status":50,"ping_status":50,"post_password":47,"post_name":65,"to_ping":47,"pinged":47,"post_modified":66,"post_modified_gmt":66,"post_content_filtered":47,"post_parent":67,"guid":68,"menu_order":53,"post_type":55,"post_mime_type":47,"comment_count":56,"filter":57,"url_path":69},17916,"2022-06-20 08:56:55","Tag Management","tag-management","2026-09-28 11:05:27",17552,"\u002F?page_id=17916","\u002Fmedia-solutions\u002Ftag-management\u002F",{"page":71,"link_text":74},{"ID":72,"post_author":45,"post_date":73,"post_date_gmt":73,"post_content":47,"post_title":74,"post_excerpt":47,"post_status":49,"comment_status":50,"ping_status":50,"post_password":47,"post_name":75,"to_ping":47,"pinged":47,"post_modified":76,"post_modified_gmt":76,"post_content_filtered":47,"post_parent":67,"guid":77,"menu_order":53,"post_type":55,"post_mime_type":47,"comment_count":56,"filter":57,"url_path":78},17140,"2022-05-27 14:22:19","Google Marketing Platform","google-marketing-platform","2026-09-25 10:43:13","\u002F?page_id=17140","\u002Fmedia-solutions\u002Fgoogle-marketing-platform\u002F",{"ID":80,"id":80,"title":81,"filename":82,"filesize":83,"url":84,"link":85,"alt":47,"author":86,"description":47,"caption":47,"name":87,"status":88,"uploaded_to":53,"date":89,"modified":89,"menu_order":53,"mime_type":90,"type":91,"subtype":92,"icon":93,"width":94,"height":95,"sizes":96},25135,"Harry-Brace2","Harry-Brace2.png",306919,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&q=90","\u002Fharry-brace2\u002F","12","harry-brace2","inherit","2023-10-03 16:03:03","image\u002Fpng","image","png","\u002Fwp\u002Fwp-includes\u002Fimages\u002Fmedia\u002Fdefault.png",696,600,{"thumbnail":97,"thumbnail-width":98,"thumbnail-height":98,"medium":99,"medium-width":100,"medium-height":101,"medium_large":102,"medium_large-width":103,"medium_large-height":104,"large":105,"large-width":106,"large-height":107,"1536x1536":108,"1536x1536-width":109,"1536x1536-height":110,"2048x2048":111,"2048x2048-width":112,"2048x2048-height":113,"post-thumbnail":114,"post-thumbnail-width":115,"post-thumbnail-height":116,"12_col":117,"12_col-width":118,"12_col-height":119,"default_landscape":120,"default_landscape-width":121,"default_landscape-height":95,"default_portrait":122,"default_portrait-width":95,"default_portrait-height":121,"6_col_and_margin_short":123,"6_col_and_margin_short-width":115,"6_col_and_margin_short-height":119,"11_col_and_margin":124,"11_col_and_margin-width":125,"11_col_and_margin-height":119,"9_col_rectangle":126,"9_col_rectangle-width":127,"9_col_rectangle-height":128,"11_col":129,"11_col-width":130,"11_col-height":119,"staff_image_696_600":131,"staff_image_696_600-width":94,"staff_image_696_600-height":95,"rectangular_thumbnail":132,"rectangular_thumbnail-width":133,"rectangular_thumbnail-height":134},"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=640&q=90&w=640","640","https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=scale&h=172&q=90&w=200",200,172,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=scale&h=662&q=90&w=768",768,662,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=1000&q=90&w=1892","1892","1000","https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=scale&h=1324&q=90&w=1536",1536,1324,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=scale&h=1766&q=90&w=2048",2048,1766,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=1180&q=90&w=1860",1860,1180,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=870&q=90&w=2880",2880,870,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=600&q=90&w=800",800,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=800&q=90&w=600","https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=870&q=90&w=1860","https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=870&q=90&w=3080",3080,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=1400&q=90&w=2150",2150,1400,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=870&q=90&w=2640",2640,"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=600&q=90&w=696","https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress%2Cformat&fit=crop&h=300&q=90&w=750",750,300,{"acf_fc_layout":136,"reduced":29,"top_overlap":137,"bottom_underlap":137,"disable_observer":-1,"heading":138,"cta_text":139,"cta_link":140,"items":141},"related_module","small","See more posts","See all articles","\u002Fblog\u002F",[142,156,166],{"type_key":17,"title":143,"excerpt":144,"to":145,"postedAt":146,"readingTime":147,"image":148,"authors":149,"category":153},"Beyond ad-level data: Unlocking granular product insights for Meta","\u003Cp>Standard Meta Ads reporting traditionally stops at the ad level, leaving e-commerce brands in the dark about which specific products are actually driving traffic on social platforms. While Dynamic Product Ads (DPAs) are incredibly powerful, they aggregate performance across multiple items, making it difficult to isolate individual product success.&nbsp; To bridge this data gap, the [&hellip;]\u003C\u002Fp>\n","\u002Fblog\u002Funlocking-granular-product-insights-for-meta\u002F","2026-06-24T14:13:48",4,"https:\u002F\u002Fimages.impression.co.uk\u002F2026\u002F06\u002Fallison-saeng-B7VlWt3pRM0-unsplash.jpg?auto=compress%2Cformat&fit=crop&h=640&q=90&w=640",[150],{"name":151,"image":152},"Zoe Le","https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F08\u002FZoe-Le-NEW.png?auto=compress&fit=crop&fm=jpg&h=150&q=80&w=150&bg=CFE6F9",{"to":154,"name":155},"\u002Fblog\u002Fcategory\u002Fmeasurement\u002F","Measurement",{"type_key":17,"title":157,"excerpt":158,"to":159,"postedAt":160,"readingTime":161,"image":162,"authors":163,"category":165},"Which Marketing Mix Modelling platform should you use?","\u003Cp>If you’ve decided to build a Marketing Mix Model (MMM), an important first step is to choose what platform you want to use. There are quite a few options, ranging from simple to complex, with different benefits to each You&#8217;ve probably come across these libraries already: Google’s Meridian, Meta&#8217;s Robyn, PyMC Marketing and a handful [&hellip;]\u003C\u002Fp>\n","\u002Fblog\u002Fwhich-marketing-mix-modelling-platform-should-you-use\u002F","2026-06-10T11:28:01",6,"https:\u002F\u002Fimages.impression.co.uk\u002F2026\u002F06\u002Fvaleria-nikitina-ie2R2t9fC9Q-unsplash.jpg?auto=compress%2Cformat&fit=crop&h=640&q=90&w=640",[164],{"name":35,"image":38},{"to":154,"name":155},{"type_key":17,"title":167,"excerpt":168,"to":169,"postedAt":170,"readingTime":171,"image":172,"authors":173,"category":180},"Beyond the click: Can you use MMM to prove the value of LLMs?","\u003Cp>LLMs (Large Language Models) have quickly become a significant influence on a customer&#8217;s journey, and all signs point to this influence only increasing. Even before we consider how to influence visibility across AI search, the first question we have to ask ourselves is: How do we measure the impact LLMs have on top-line results? The [&hellip;]\u003C\u002Fp>\n","\u002Fblog\u002Fcan-mmm-prove-the-value-of-lmms\u002F","2026-04-28T11:48:18",8,"https:\u002F\u002Fimages.impression.co.uk\u002F2026\u002F04\u002Faerps-com-bUUrG6CMHiA-unsplash.jpg?auto=compress%2Cformat&fit=crop&h=640&q=90&w=640",[174,177],{"name":175,"image":176},"Alex Howat","https:\u002F\u002Fimages.impression.co.uk\u002F2021\u002F06\u002FkMgPqCLz-Alex-Howat.png?auto=compress&fit=crop&fm=jpg&h=150&q=80&w=150&bg=CFE6F9",{"name":178,"image":179},"Petar Jovetic","https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F08\u002FPete-Jovetic-NEW.png?auto=compress&fit=crop&fm=jpg&h=150&q=80&w=150&bg=CFE6F9",{"to":154,"name":155},{"type":182,"style":183,"heading":30,"date":4,"updatedAt":184,"reading_minutes":147,"image":185,"imageAlt":30,"categories":186,"collections":452},"blog-post","light","2025-04-16T15:37:06","https:\u002F\u002Fimages.impression.co.uk\u002F2025\u002F04\u002Fkamran-abdullayev-wth383_dXjw-unsplash.jpg?auto=compress%2Cformat&fit=crop&h=1180&q=90&w=1860",[187,367],{"id":10,"count":188,"description":189,"link":190,"name":191,"slug":192,"taxonomy":193,"parent":53,"meta":194,"acf":195,"head_links":196,"resource_count":53,"yoast_title":197,"yoast_meta":198,"yoast_json_ld":241,"_links":339,"path":190},10,"Behind the scenes of any good advertising campaign, customer experience or \u003Ca href=\"\u002Fmedia-solutions\u002Fmeasurement\u002F\">data analysis\u003C\u002Fa> is the lifting, shifting and transformation of millions of rows of raw data. At Impression our \u003Ca href=\"\u002Fmedia-solutions\u002F\">Solutions\u003C\u002Fa> team comprises data engineers familiar with advertising platforms, APIs, various industry tooling and web scraping -- and of course databases like \u003Ca href=\"\u002Fmedia-solutions\u002Fmodern-data-stack\u002F\">customer data platforms\u003C\u002Fa>. Check out the posts below.","\u002Fblog\u002Fcategory\u002Fdata-engineering\u002F","Data Engineering","data-engineering","category",[],{"hidden":7,"sub_title_override":191,"title_override":47},[],"Data Engineering - Impression",[199,201,204,207,210,213,215,218,220,223,226,229,232,235,238],{"property":200,"content":197},"title",{"name":202,"content":203},"robots","index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1",{"property":205,"content":206},"canonical","https:\u002F\u002Fadmin.impressiondigital.com\u002Fblog\u002Fcategory\u002Fdata-engineering\u002F",{"name":208,"content":209},"og:locale","en-GB",{"property":211,"content":212},"og:type","article",{"property":214,"content":197},"og:title",{"property":216,"content":217},"og:description","Behind the scenes of any good advertising campaign, customer experience or data analysis is the lifting, shifting and transformation of millions of rows of raw data. At Impression our Solutions team comprises data engineers familiar with advertising platforms, APIs, various industry tooling and web scraping &#8212; and of course databases like customer data platforms. Check out the posts below.",{"property":219,"content":206},"og:url",{"property":221,"content":222},"og:site_name","Impression",{"property":224,"content":225},"og:image","https:\u002F\u002Fimages.impression.co.uk\u002F2021\u002F06\u002FABFPXguH-Opengraph-BLUE.jpg?auto=compress%2Cformat&q=90",{"property":227,"content":228},"og:image:width",1200,{"property":230,"content":231},"og:image:height",630,{"property":233,"content":234},"og:image:type","image\u002Fjpeg",{"property":236,"content":237},"twitter:card","summary_large_image",{"property":239,"content":240},"twitter:site","@impressiontalk",{"@context":242,"@graph":243},"https:\u002F\u002Fschema.org",[244,252,262,272],{"@type":245,"@id":246,"url":246,"name":197,"isPartOf":247,"breadcrumb":249,"inLanguage":251},"CollectionPage","https:\u002F\u002Fwww.impressiondigital.com\u002Fblog\u002Fcategory\u002Fdata-engineering\u002F",{"@id":248},"https:\u002F\u002Fwww.impressiondigital.com\u002F#website",{"@id":250},"https:\u002F\u002Fwww.impressiondigital.com\u002Fblog\u002Fcategory\u002Fdata-engineering\u002F#breadcrumb","en",{"@type":253,"@id":250,"itemListElement":254},"BreadcrumbList",[255,260],{"@type":256,"position":257,"name":258,"item":259},"ListItem",1,"Home","https:\u002F\u002Fwww.impressiondigital.com\u002F",{"@type":256,"position":261,"name":191},2,{"@type":263,"@id":248,"url":259,"name":222,"description":47,"publisher":264,"inLanguage":209,"potentialAction":266},"WebSite",{"@id":265},"https:\u002F\u002Fwww.impressiondigital.com\u002F#organization",{"@type":267,"target":268,"query-input":271},"SearchAction",{"@type":269,"urlTemplate":270},"EntryPoint","https:\u002F\u002Fwww.impressiondigital.com\u002Fsearch?q={search_term_string}","required name=search_term_string",{"@type":273,"@id":265,"name":222,"url":259,"logo":274,"image":280,"sameAs":281,"@context":285,"email":286,"foundingDate":287,"legalName":288,"vatID":289,"description":290,"telephone":291,"address":292,"location":299,"areaServed":332},"Organization",{"@type":275,"inLanguage":209,"@id":276,"url":277,"contentUrl":277,"width":278,"height":279,"caption":222},"ImageObject","https:\u002F\u002Fwww.impressiondigital.com\u002F#\u002Fschema\u002Flogo\u002Fimage\u002F","https:\u002F\u002Fcdn.impression.co.uk\u002F2021\u002F06\u002FA5LuTDrq-Impression_Wordmark.png",920,176,"https:\u002F\u002Fcdn.impression.co.uk\u002F2021\u002F04\u002FFAVxDeOS-Nottingham.jpg",[282,283,284],"https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fimpression-digital-limited","https:\u002F\u002Fwww.facebook.com\u002Fimpression\u002F","https:\u002F\u002Fwww.instagram.com\u002Fimpressiontalk\u002F","https:\u002F\u002Fwww.schema.org\u002F","hello@impressiondigital.com","2012-11-07","Impression Digital Limited","GB186363774","Impression is an award-winning digital marketing agency based in the UK and USA. We offer SEO agency, PPC agency, Digital PR agency and Analytics services to companies of all sizes across the UK, North America, Europe and beyond. Get in touch with us if you think we can work together.","01158 242 212",{"@type":293,"streetAddress":294,"addressLocality":295,"addressRegion":296,"postalCode":297,"addressCountry":298},"PostalAddress","Fothergill House, 16 King Street","Nottingham","Nottinghamshire","NG1 2AS","United Kingdom",[300,309,321],{"@type":301,"name":302,"geo":303,"address":307,"photo":280,"telephone":308},"Place","Impression Digital - Nottingham",{"@type":304,"latitude":305,"longitude":306},"GeoCoordinates","52.95501401025914","-1.1494887460285232",{"@type":293,"streetAddress":294,"addressLocality":295,"addressRegion":296,"postalCode":297,"addressCountry":298},"+44 01158 242 212",{"@type":301,"name":310,"geo":311,"address":314,"photo":319,"telephone":320},"Impression Digital - London",{"@type":304,"latitude":312,"longitude":313},"51.50237208377361","-0.09229841534284115",{"@type":293,"streetAddress":315,"addressLocality":316,"addressRegion":317,"postalCode":318,"addressCountry":298},"201 Borough High St","Southwark","London","SE1 1JA","https:\u002F\u002Fcdn.impression.co.uk\u002F2021\u002F04\u002FwD0pPVWz-London.jpg","+44 020 7112 8148",{"@type":301,"name":322,"geo":323,"address":326},"Impression Digital - New York",{"@type":304,"latitude":324,"longitude":325},"40.726722746949","-74.00527778220652",{"@type":293,"streetAddress":327,"addressLocality":328,"addressRegion":329,"postalCode":330,"addressCountry":331},"160 Varick St","New York","NY","10013","USA",[333,336,338],{"@type":334,"name":335},"Country","Worldwide",{"@type":334,"name":337},"GBR",{"@type":334,"name":331},{"self":340,"collection":346,"about":349,"wp:post_type":352,"curies":363},[341],{"href":342,"targetHints":343},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fcategories\u002F280",{"allow":344},[345],"GET",[347],{"href":348},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fcategories",[350],{"href":351},"\u002Fwp-json\u002Fwp\u002Fv2\u002Ftaxonomies\u002Fcategory",[353,355,357,359,361],{"href":354},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts?categories=280",{"href":356},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fwhite_papers?categories=280",{"href":358},"\u002Fwp-json\u002Fwp\u002Fv2\u002Ftools?categories=280",{"href":360},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fwebinars?categories=280",{"href":362},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fevents?categories=280",[364],{"name":365,"href":366,"templated":29},"wp","https:\u002F\u002Fapi.w.org\u002F{rel}",{"id":11,"count":368,"description":369,"link":154,"name":155,"slug":370,"taxonomy":193,"parent":53,"meta":371,"acf":372,"head_links":373,"resource_count":374,"yoast_title":375,"yoast_meta":376,"yoast_json_ld":396,"_links":429,"path":154},131,"Here at Impression, ongoing research and training is a huge part of how we keep our \u003Ca href=\"\u002Fmedia-solutions\u002F\">Media Solutions\u003C\u002Fa> team up-to-date with the latest happenings in the world of web &amp; app analytics, martech, \u003Ca href=\"\u002Fmedia-solutions\u002Fdata-science\u002F\">data science\u003C\u002Fa> and \u003Ca href=\"\u002Fmedia-solutions\u002Fmedia-effectiveness\u002F\">media effectiveness\u003C\u002Fa>. We regularly share our thoughts on the latest digital news right here on our blog, so you can keep up to date too.\r\n\r\nFind out more about our \u003Ca href=\"\u002Fanalytics\u002F\">Analytics Agency\u003C\u002Fa> services, or browse our latest tips, advice and opinions below.","measurement",[],{"sub_title_override":47,"title_override":47},[],23,"Online Measurement, Analytics & Effectiveness Blog | Impression",[377,378,381,382,384,385,386,387,388,389,390,391,392,393,394,395],{"property":200,"content":375},{"property":379,"content":380},"description","Keeping up to date with the latest measurement and analytics trends and strategies can be difficult. Browse our tips and advice in our latest blogs!",{"name":202,"content":203},{"property":205,"content":383},"https:\u002F\u002Fadmin.impressiondigital.com\u002Fblog\u002Fcategory\u002Fmeasurement\u002F",{"name":208,"content":209},{"property":211,"content":212},{"property":214,"content":375},{"property":216,"content":380},{"property":219,"content":383},{"property":221,"content":222},{"property":224,"content":225},{"property":227,"content":228},{"property":230,"content":231},{"property":233,"content":234},{"property":236,"content":237},{"property":239,"content":240},{"@context":242,"@graph":397},[398,403,407,411],{"@type":245,"@id":399,"url":399,"name":375,"isPartOf":400,"description":380,"breadcrumb":401,"inLanguage":251},"https:\u002F\u002Fwww.impressiondigital.com\u002Fblog\u002Fcategory\u002Fmeasurement\u002F",{"@id":248},{"@id":402},"https:\u002F\u002Fwww.impressiondigital.com\u002Fblog\u002Fcategory\u002Fmeasurement\u002F#breadcrumb",{"@type":253,"@id":402,"itemListElement":404},[405,406],{"@type":256,"position":257,"name":258,"item":259},{"@type":256,"position":261,"name":155},{"@type":263,"@id":248,"url":259,"name":222,"description":47,"publisher":408,"inLanguage":209,"potentialAction":409},{"@id":265},{"@type":267,"target":410,"query-input":271},{"@type":269,"urlTemplate":270},{"@type":273,"@id":265,"name":222,"url":259,"logo":412,"image":280,"sameAs":413,"@context":285,"email":286,"foundingDate":287,"legalName":288,"vatID":289,"description":290,"telephone":291,"address":414,"location":415,"areaServed":425},{"@type":275,"inLanguage":209,"@id":276,"url":277,"contentUrl":277,"width":278,"height":279,"caption":222},[282,283,284],{"@type":293,"streetAddress":294,"addressLocality":295,"addressRegion":296,"postalCode":297,"addressCountry":298},[416,419,422],{"@type":301,"name":302,"geo":417,"address":418,"photo":280,"telephone":308},{"@type":304,"latitude":305,"longitude":306},{"@type":293,"streetAddress":294,"addressLocality":295,"addressRegion":296,"postalCode":297,"addressCountry":298},{"@type":301,"name":310,"geo":420,"address":421,"photo":319,"telephone":320},{"@type":304,"latitude":312,"longitude":313},{"@type":293,"streetAddress":315,"addressLocality":316,"addressRegion":317,"postalCode":318,"addressCountry":298},{"@type":301,"name":322,"geo":423,"address":424},{"@type":304,"latitude":324,"longitude":325},{"@type":293,"streetAddress":327,"addressLocality":328,"addressRegion":329,"postalCode":330,"addressCountry":331},[426,427,428],{"@type":334,"name":335},{"@type":334,"name":337},{"@type":334,"name":331},{"self":430,"collection":435,"about":437,"wp:post_type":439,"curies":450},[431],{"href":432,"targetHints":433},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fcategories\u002F41",{"allow":434},[345],[436],{"href":348},[438],{"href":351},[440,442,444,446,448],{"href":441},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts?categories=41",{"href":443},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fwhite_papers?categories=41",{"href":445},"\u002Fwp-json\u002Fwp\u002Fv2\u002Ftools?categories=41",{"href":447},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fwebinars?categories=41",{"href":449},"\u002Fwp-json\u002Fwp\u002Fv2\u002Fevents?categories=41",[451],{"name":365,"href":366,"templated":29},[],[],[455,457,459,460],{"path":456,"name":258},"\u002F",{"path":140,"name":458},"Blog",{"path":154,"name":155},{"path":461,"name":30},null,[463,464],{"id":10,"name":191,"path":190},{"id":11,"name":155,"path":154},{"title":466,"script":467,"meta":539,"link":569},"Meridian: Google’s Answer to Marketing Mix Modelling | Impression",[468],{"type":469,"key":470,"innerHTML":471},"application\u002Fld+json","yoast-json-ld",{"@context":242,"@graph":472},[473,490,497,500,508,512,530],{"@type":474,"@id":475,"isPartOf":476,"author":478,"headline":30,"datePublished":480,"dateModified":481,"mainEntityOfPage":482,"wordCount":483,"publisher":484,"image":486,"thumbnailUrl":488,"articleSection":489,"inLanguage":209},"Article","https:\u002F\u002Fwww.impressiondigital.com\u002Fblog\u002Fmeridian-googles-marketing-mix-modelling\u002F#article",{"@id":477},"https:\u002F\u002Fwww.impressiondigital.com\u002Fblog\u002Fmeridian-googles-marketing-mix-modelling\u002F",{"name":35,"@id":479},"https:\u002F\u002Fadmin.impressiondigital.com\u002F#\u002Fschema\u002Fperson\u002Fa18b79c97abbcb2444ace02aa88250ae","2025-04-16T15:37:05+00:00","2025-04-16T15:37:06+00:00",{"@id":477},846,{"@id":485},"https:\u002F\u002Fadmin.impressiondigital.com\u002F#organization",{"@id":487},"https:\u002F\u002Fwww.impressiondigital.com\u002Fblog\u002Fmeridian-googles-marketing-mix-modelling\u002F#primaryimage","https:\u002F\u002Fimages.impression.co.uk\u002F2025\u002F04\u002Fkamran-abdullayev-wth383_dXjw-unsplash.jpg?auto=compress%2Cformat&q=90",[191,155],{"@type":491,"@id":477,"url":477,"name":466,"isPartOf":492,"primaryImageOfPage":493,"image":494,"thumbnailUrl":488,"datePublished":480,"dateModified":481,"breadcrumb":495,"inLanguage":251},"WebPage",{"@id":248},{"@id":487},{"@id":487},{"@id":496},"https:\u002F\u002Fwww.impressiondigital.com\u002Fblog\u002Fmeridian-googles-marketing-mix-modelling\u002F#breadcrumb",{"@type":275,"inLanguage":209,"@id":487,"url":488,"contentUrl":488,"width":498,"height":499},2400,1350,{"@type":253,"@id":496,"itemListElement":501},[502,503,505,507],{"@type":256,"position":257,"name":258,"item":259},{"@type":256,"position":261,"name":458,"item":504},"https:\u002F\u002Fwww.impressiondigital.com\u002Fblog\u002F",{"@type":256,"position":506,"name":155,"item":399},3,{"@type":256,"position":147,"name":30},{"@type":263,"@id":248,"url":259,"name":222,"description":47,"publisher":509,"inLanguage":209,"potentialAction":510},{"@id":265},{"@type":267,"target":511,"query-input":271},{"@type":269,"urlTemplate":270},{"@type":273,"@id":265,"name":222,"url":259,"logo":513,"image":280,"sameAs":514,"@context":285,"email":286,"foundingDate":287,"legalName":288,"vatID":289,"description":290,"telephone":291,"address":515,"location":516,"areaServed":526},{"@type":275,"inLanguage":209,"@id":276,"url":277,"contentUrl":277,"width":278,"height":279,"caption":222},[282,283,284],{"@type":293,"streetAddress":294,"addressLocality":295,"addressRegion":296,"postalCode":297,"addressCountry":298},[517,520,523],{"@type":301,"name":302,"geo":518,"address":519,"photo":280,"telephone":308},{"@type":304,"latitude":305,"longitude":306},{"@type":293,"streetAddress":294,"addressLocality":295,"addressRegion":296,"postalCode":297,"addressCountry":298},{"@type":301,"name":310,"geo":521,"address":522,"photo":319,"telephone":320},{"@type":304,"latitude":312,"longitude":313},{"@type":293,"streetAddress":315,"addressLocality":316,"addressRegion":317,"postalCode":318,"addressCountry":298},{"@type":301,"name":322,"geo":524,"address":525},{"@type":304,"latitude":324,"longitude":325},{"@type":293,"streetAddress":327,"addressLocality":328,"addressRegion":329,"postalCode":330,"addressCountry":331},[527,528,529],{"@type":334,"name":335},{"@type":334,"name":337},{"@type":334,"name":331},{"@type":531,"@id":532,"name":35,"image":533,"description":37,"sameAs":536,"url":538},"Person","https:\u002F\u002Fwww.impressiondigital.com\u002F#\u002Fschema\u002Fperson\u002Fa18b79c97abbcb2444ace02aa88250ae",{"@type":275,"inLanguage":209,"@id":534,"url":535,"contentUrl":535,"caption":35},"https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress&fit=fit&fm=jpg&h=96&q=90&w=9615847ead018a2de28b7216e39fc92f32","https:\u002F\u002Fimages.impression.co.uk\u002F2023\u002F10\u002FHarry-Brace2.png?auto=compress&fit=fit&fm=jpg&h=96&q=90&w=96",[537],"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fharrison-brace-137b8482\u002F","https:\u002F\u002Fwww.impressiondigital.com\u002Fabout\u002Four-team\u002Fharry-brace\u002F",[540,541,543,544,545,547,548,549,552,554,556,558,559,560,561,563,564,566,568],{"name":202,"content":203},{"property":208,"content":542},"en_GB",{"property":211,"content":212},{"property":214,"content":466},{"property":216,"content":546},"Ever since Google announced that it would be releasing an open-source Media Mix Modelling (MMM) package, which adds to and improves upon its predecessor, LightweightMMM, data scientists and marketers have been eagerly waiting for access to the platform. Most were left waiting until Google announced they would release it to the world on the 29th [&hellip;]",{"property":219,"content":477},{"property":221,"content":222},{"property":550,"content":551},"article:publisher","https:\u002F\u002Fwww.facebook.com\u002Fimpression",{"property":553,"content":480},"article:published_time",{"property":555,"content":481},"article:modified_time",{"property":224,"content":557},"https:\u002F\u002Fimages.impression.co.uk\u002F2025\u002F04\u002Fopen-graph-an-introduction-to-whatsapp-advertising.png?auto=compress%2Cformat&q=90",{"property":227,"content":228},{"property":230,"content":231},{"property":233,"content":90},{"name":562,"content":35},"author",{"name":236,"content":237},{"name":565,"content":557},"twitter:image",{"name":567,"content":240},"twitter:creator",{"name":239,"content":240},[]]