L'Oréal Luxe drives sales growth for D2C website by untapping hidden potential with Conversion Modelling
Learn how the L'Oréal Luxe team has been using SegmentStream to gain accurate marketing attribution insights and achieve a serious ad performance uplift, resulting in 41% ROAS improvement across the whole Marketing Mix.

“This project's success unlocked new opportunities for the brand in the market, and now we are scaling it to other luxury brands in our market and region.”
— Perla Patricia Aragon, Chief Digital Officer, L'Oréal Luxe Latin America
About the client
L’Oréal Luxe delivers a unique product and brand experience to its consumers. With a diverse portfolio of 26 brands, they cater to the needs of all consumer tribes, across various price levels.
The company’s portfolio consists of 26 exceptional brands, including 17 global ones such as Lancôme, Yves Saint Laurent, and Giorgio Armani.
L’Oréal Luxe is known for its commitment to research and innovation and has been at the forefront of developments in the beauty industry for over a century.
L’Oreal Luxe Partners SegmentStream
The partnership with SegmentStream started with one brand, Lancôme Mexico, and after the successful pilot, it is now being rolled out to other L’Oréal brands and markets.
The challenges:
The primary focus for Lancôme Mexico was to increase sales on their Direct-to-Consumer (D2C) website. To achieve this goal, the team was looking to solve three core challenges.
- Maximise D2C website media efficiency through optimal Marketing Mix
People who are looking to buy luxury cosmetic products, such as Lancôme, often visit the website multiple times before making a purchase, often using multiple devices and browsers in their customer journeys.
Due to the long and complex path to a conversion, it becomes challenging to accurately measure how different marketing channels and campaigns actually contribute to the total number of sales and revenue.
This is especially an issue when measuring the performance of prospecting campaigns that are designed to drive initial awareness and not immediate sales.
While upper-funnel marketing activities drive serious incremental contribution to future sales, they often do not receive any sales credit. Due to multiple modern-day cookie tracking restrictions and complex, multi-device customer journeys, in most cases, the actual conversion will not be attributed to the initial traffic source.
Without clear visibility into the real sales impact of each media traffic source, it is impossible to understand the true Return on Ad Spend of each channel and campaign and make timely and efficient budget allocation decisions to achieve the optimal Marketing Mix.
To maximise media efficiency on the D2C website, the Lancôme Mexico team had to gain insights into which paid traffic sources drive value to the business, even when they do not result in immediate conversions.
- Enhance ad optimisation with additional conversion signals
Lancôme Mexico primarily invests in two ad platforms to drive website traffic and sales: Facebook Ads and Google Ads. Both of these ad platforms heavily rely on conversion signals for efficient campaign learning and optimisation. Therefore, it is essential to provide ad platforms with timely and accurate data feedback about the true value of each click.
However, when buying journeys are long and complex, ad platforms’ clicks often do not receive properly attributed value, which prevents ad platforms from reaching their full potential. For example, Facebook Ad Manager has a 7-day attribution window, which means that conversions will not be attributed to Facebook Ads if the purchase did not happen within this timeframe. Due to this, even if the ad campaigns drive highly-engaged users to the website which will often purchase later, the ad platform will not receive any insight about the actual value of this particular click.
This is especially challenging when running prospecting campaigns that focus on driving initial awareness and not immediate sales. Such a lack of conversion signals seriously restricts ad platforms from effective auto-bidding and targeting.
Therefore, to ensure maximum performance from digital advertising, Lancôme Mexico had to find a way to provide ad platforms with information about the true value of each ad click, even if it did not result in an immediate conversion right away.
- Gain more agility in day-to-day media team operations
To ensure optimal results from digital marketing efforts, it is crucial to prioritise high-value marketing activities while automating routine tasks. Unfortunately, marketers often spend too much time generating reports and analysing data to determine the effectiveness of their paid media campaigns, especially when managing multiple advertising platforms and numerous product promotions.
The team at Lancôme experienced a similar challenge, as their weekly marketing reporting and media performance analysis were time-consuming. To overcome these obstacles, they had to automate their reporting processes to quickly obtain insights into media performance, with the goal of freeing up resources for their e-commerce and media team.
By redirecting the saved time towards more productive activities, my ecommerce and digital team could focus on strategic marketing projects, such as developing a better targeting strategy and value proposition for customers. Therefore, it was crucial to achieve agility in day-to-day operations and gain real-time visibility into media mix performance.
— Erendira Garibay, Digital Director L’Oreal Luxe Mexico
To overcome these challenges and generate more qualified prospects, the team at Lancôme Mexico decided to test an innovative marketing attribution approach called SegmentStream’s Conversion Modelling.
SegmentStream — solution overview:
SegmentStream is a Conversion Modelling Platform that uses the power of AI and first-party data to achieve accurate marketing measurement and efficient ad optimisation in a truly innovative and unique way.
Why is SegmentStream unique?
Traditionally, marketing measurement solutions relied on tracking the actual conversion and then attributed the value from this conversion to one or more traffic sources within a customer journey.
However, this retrospective approach to marketing attribution is essentially broken. Due to modern-day cookie restrictions, cross-device/browser interactions and short attribution windows, it is no longer able to track a complete user’s path to a conversion.
As the result, both analytics and ad platforms are no longer able to attribute conversions and value properly — the majority of website visits do not get any value even if they seriously contribute to conversions and revenue.
The aim of Conversion Modelling is to discover which traffic sources drive the most incremental value to the business, even when they do not result in directly attributed sales.
Unlike such solutions, SegmentStream’s Conversion Modelling approach relies on proprietary Machine Learning algorithms to evaluate each website visit and measure its incremental contribution to the future conversion.
This way, each traffic source finally gets the true value it deserves, even if the real conversion happens from another device, browser, or cookie, and will not be attributed to the traffic source directly.
By using SegmentStream Conversion Modelling Platform, marketers can gain better visibility into the true value of their digital channels and campaigns, while ad platforms start to perform better by receiving accurate, real-time attribution data about the incremental value of each click.
Use Case #1: Accurate Measurement & Marketing Mix Evaluation
SegmentStream ensures an accurate evaluation of all paid media traffic sources even when the final conversion cannot be observed due to modern tracking restrictions and complex user journeys.
By finally knowing the true impact of all paid media traffic sources, marketers can make correct, timely and confident budget allocation decisions to ensure the optimal Marketing Mix and achieve the highest total ROI from the overall advertising spend.
Accurate evaluation of all paid media traffic sources with SegmentStream
Use Case #2: Enhanced Ad Targeting & Optimisation
SegmentStream unlocks the full potential of the ad campaigns by providing immediate feedback about the true value of each click.
By amplifying ad platforms, such as Google & Facebook, with real-time value signals, marketers can expect a much better return on their ad spend, as targeting algorithms start to learn & optimise much faster, focusing ad spending on the audience who is most likely to drive value to the business.
SegmentStream amplifies ad platforms with real-time value signals
The implementation process:
Let’s see how this approach worked in the Lancôme Mexico case.
SegmentStream solution for Lancôme Mexico
Step 1: Website data collection
SegmentStream relies on Machine Learning to analyse the impact of each website visit. To build an accurate ML model, SegmentStream requires first-party data about user behaviour on the website.
Lancôme Mexico uses Google Analytics 360 to collect website events, which are then securely stored in their own Google BigQuery account. This first-party user data is then used by SegmentStream to train a highly accurate Machine Learning model, predicting the probability of each user’s purchase.
Step 2: Advertising data collection
Lancôme Mexico runs marketing activities across Google Ads and Facebook Ads. SegmentStream already has turn-key integrations with the most popular advertising platforms, so the setup takes very little time.
SegmentStream collects data about clicks, costs, and ad impressions, and stitches it with website sessions and conversions automatically.
This helped the Lancôme Mexico team to obtain a full cross-channel view of the company’s marketing activities in a single easy-to-use interface.
Step 3: Conversion Modelling
Using Machine Learning, SegmentStream analyses each website visit to measure the user’s conversion probability and predicted conversion value based on the user behaviour and other 1st-party data, unique for Lancôme Mexico.
If the contribution to a future conversion was significant, the website visit will be considered valuable. In this case, the Modelled Conversion will be created and immediately attributed to this website visit, and the traffic source that initiated the visit.
This way, each traffic source finally gets the value it deserves even if the real conversion will happen from another device, browser, or cookie.
For a deeper dive into the topic of Conversion Modelling technology, read our guide for performance marketers.
Benefits and advantages for Lancôme Mexico
Once the SegmentStream platform was implemented and fully set up, Lancôme Mexico could immediately start getting benefits out of it, achieving two primary use cases:
Marketing Measurement & Media Mix Evaluation
SegmentStream platform provided Lancôme Mexico with a comprehensive overview of their campaigns’ performance, which included information about the actual incremental value of each marketing channel and campaign.
Conversion Modelling insights enabled Lancôme Mexico with a better understanding of how different marketing sources contribute to the total number of purchases, even if the actual conversion will not be attributed directly.
With this powerful knowledge, the Lancôme Mexico team could make informed budget allocation decisions to optimise their marketing mix and achieve the best return on investment (ROI).
It is also worth noting that the entire reporting was fully automated which means that the e-commerce & media team could now allocate more time to strategic projects, rather than manual data crunching & reporting.
SegmentStream demo data dashboard
Enhanced Ad Campaign Optimisation using Modelled Conversions
Once Lancôme Mexico set up a seamless, automated export of SegmentStream’s Modelled Conversions to Google Ads and Facebook Ads, both ad platforms could start leveraging these additional value signals for improved targeting & campaign optimisation.
Such real-time attribution insights help both Meta and Google train their smart bidding algorithms more effectively, leading to higher performance and ROI.
Enhanced ad campaign optimisation using Modelled Conversions
To ensure that Modelled Conversions drive incremental uplift, Lancôme Mexico together with SegmentStream’s Customer Success team ran multiple experiments to ensure that Conversion Modelling drives value in a repeatable way.
Business results:
1. Improved agility and overall visibility into Media Mix performance
The Lancôme’s Mexico team utilised SegmentStream’s capabilities to enhance the agility of their agency and media teams’ operations through automation and real-time access to the most important marketing data.
By implementing SegmentStream’s platform, Lancôme’s e-commerce and media teams were able to concentrate on business strategy and direction.
With the Conversion Modelling Platform, Lancôme’s team gained more comprehensive and detailed insights into their marketing activities’ performance, enabling them to refocus their efforts more effectively.
As a result, the team identified the optimal marketing mix and improved their value proposition to customers, driving business growth for their D2C website.
2. Data-driven budget reallocation resulted in 41% ROAS improvement across the whole Marketing Mix
By gaining visibility into the true incremental impact of each paid media channel and campaign, the Lancôme Mexico team was finally able to uncover the actual Return of Ad Spend across their entire digital marketing mix.
Before using Conversion Modelling, Prospecting campaigns on Facebook were heavily undervalued — they generated a small number of attributed conversions compared to Google Search, which has similar ad spend but resulted in much more direct sales.
However, SegmentStream revealed that Facebook actually had a similar contribution to total sales as Google Search, which justified its investment and even opened an opportunity to scale.
— Jose Avila, Media Manager L’Oreal Luxe Mexico
Thanks to SegmentStream insights, the Lancôme Mexico team reallocated more budget towards Facebook and was able to get +8% more Purchases along with -28% CPA and +41% ROAS improvement across the whole Marketing Mix.
3. Improved performance of advertising platforms generated 57% increase in purchases
With the help of SegmentStream’s Conversion Modelling Platform, Lancôme Mexico was able to enhance ad platform’s algorithms with real-time signals about the actual incremental value of each ad click, even if the click did not result in a directly attributed conversion.
By providing more value signals to Google Ads, in less than two months, Lancôme experienced a powerful incremental uplift in ad performance:
- 57% increase in purchases
- 59% decrease in CPA
- 156% increase in ROAS
Additionally, after the campaign started to optimise towards SegmentStream Modelled Conversions, it has attracted 34% more high-value website visitors at 52% lower cost, when compared to the previous period, before optimisation was enabled.
Fragrances Branded Search experiment:
To ensure that Conversion Modelling delivers uplift in a repeatable way, the Lancôme Mexico team also conducted an A/B test on one of their largest sub-branded campaigns, Fragrances.
The test branch was optimised with SegmentStream Conversion Event (combined with the Purchase event), while the control branch continued to be optimised with the Purchase event only.
During the experiment period, the test branch resulted in 67% more Purchases at a 48% lower CPA compared to the control branch. It also generated 2x more high-value website visitors at a 60% lower cost.
As the result, SegmentStream’s ad optimisation capabilities helped the L’Oréal Luxury Division team to drive much more revenue for their D2C website when feeding ad platforms with more timely and accurate attribution data. This proved to be an effective way to increase campaign performance for brands with long and complex customer journeys, such as Lancôme.
Customer testimonial:
For a while, we have been searching for the right solution to gain insights into our media mix performance, as we understood that marketing attribution in a traditional way became challenging due to modern limitations in customer journey tracking.
We found SegmentStream’s approach to marketing measurement to be innovative and unique. It was designed to work in a cookie-less world. We liked the concept of evaluating each website visit using Machine Learning. It meant that we could finally gain visibility into the actual sales impact of our paid media traffic sources, and understand their incremental contribution to our bottom line.
We decided to launch a pilot of the Conversion Modelling in Lancôme Mexico, and we’re glad that we did it. SegmentStream proved to be an effective tool in fueling the e-commerce success of the Lancôme Mexico D2C website.
We were able to improve the performance of our digital ad campaigns, make informed budget allocation decisions, and achieve a positive uplift in sales by finding new revenue opportunities. Moreover, SegmentStream helped us give back precious time to our media and e-commerce team, and made our day-to-day operations much more agile.
We would like to thank the team for helping us during our journey. This project’s success unlocked new opportunities for the brand in the market, and now we are scaling it to other luxury brands in our market and region. We are certain this project will positively impact our business activation.
— Perla Patricia Aragon, Chief Digital Officer, L’Oréal Luxe Latin America
Never miss an article
Get the latest articles, event invitations and product updates delivered straight to your inbox.
Thank you! You’ve been signed up for our newsletter.
Get started with SegmentStream
Learn about Conversion Modelling and why it is a true next-generation solution to outdated marketing attribution and conversion tracking tools.