Business Value of Attribution AI

Luma, an athletic apparel retailer, recently launched a new line of products, LumaSmart Hoshi leggings. They used Adobe’s Intelligent Services to identify the right audience - to target with Customer AI, and ran a marketing campaign - to personalize content to those users across channels. Now we’re going to show you how Luma harnesses the power of Attribution AI to understand which marketing channels were most effective in driving - incremental conversions of LumaSmart sales, and - where Luma should optimize their marketing spend to be - most efficient moving forward. And we’ll show you how - they can do all this without needing a team of data scientists. One of the biggest - challenges for marketers that run multi-touch campaigns is understanding which channels drive the most incremental - impact on conversions beyond the baseline that - would have occurred anyway as a result of brand equity, for example. Attribution AI addresses - this challenge head-on, as it learns the most accurate - model for each customer by training on their specific - data asset and use case. It compares and contrasts - the converted path versus non-converted customer path through supervised machine - learning techniques, combined with other relevant - state-of-the-art technologies. So, why is Attribution AI better than traditional rules-based attribution? Well, rules-based - attribution uses the same pre-defined formulas - across different customers, data sets, and use cases. And it does not address true causality or correlation between the - touchpoints and conversions. Now, out with the old and in with the new. Let’s use Attribution AI - to create a new instance to identify the true marketing - impact of LumaSmart orders. We’re guided through another - simple three step workflow to set up this powerful Attribution AI. I’ll give it a name and - configure my data sources that I’ve already prepared and mapped. We’ll define my conversion - of event that they purchased, and select the product category. We can set the look-back window, and define the touchpoints to report on. We’ll add social, email, - direct, display, and more. Next, we’ll set the schedule - for when and how often we want these attribution - scores to be generated. We can enable region-based modeling to understand how - different regions perform at the country level for global campaigns, as customers may behave differently. And we can set the historical look-back for training the model. And, voila, the new attribution instance for LumaSmart orders is complete! And once the model has been trained, we can click into the insights. Attribution AI delivers two unique scores that provide greater accuracy in quantifying marketing impact. The most powerful score - is the incremental score, which is the amount of marginal impact directly caused by the - marketing touchpoint, taking into account - baseline LumaSmart orders, if there were zero marketing efforts. Then, there’s the influence score, which is the fraction of the conversion that each marketing - touchpoint is responsible for. While these attribution - insights are presented at the aggregate level in this dashboard, we can also download the scores as a CSV from this interface, or through the APIs, to get these insights at - the most granular level to power custom dashboards - through BI tools like Microsoft’s Power - BI, Tableau, or Looker. It’s clear that Attribution AI delivers the most accurate insights. Thanks to this intelligence, - we can confidently optimize our marketing spend across and - within channels and campaigns that yield the highest ROI. In summary, we can see - how intelligent services can help us understand how to - drive incremental conversions efficiently, with Attribution AI. With Intelligent Services, - brands like Luma can scale, and start turning - insights to action faster, letting machine learning - take on the complexities, so marketers can work smarter, not harder. Welcome to the next era of - Experience Intelligence. -