The beauty industry today is embracing cutting-edge technology to stay ahead of microtrends and streamline product development, all while improving efficiency and innovation in an increasingly fast-paced market. Brand loyalty is no longer solely dictated by legacy brands; “digital-first” challengers are capitalizing on changing consumer preferences and behaviors. Global Industry Cosmetics Magazine found that 6.2% of beauty sales now come from social selling platforms, with TikTok alone capturing 2.6% of the market. Nearly 41% of all beauty and personal care product sales now happen online, according to NielsenIQ’s Global State of Beauty 2025 report.

Virtual try-on apps, AI/ML-based product recommendations, smart applicators for hair and skin products – the beauty industry is testing, scaling, and rapidly deploying solutions to satisfy consumers who demand personalized experiences that cater to their unique needs. Based on our observations, and conversations with leaders in beauty & cosmetics retailing, we found that to thrive in this dynamic landscape, there is a need to move beyond traditional customer segmentation and delve deeper into customer product affinity.

What is customer product affinity embedding?

Imagine a complex map where customers and products are not locations but points in a multidimensional space. Customer product affinity embedding uses advanced machine learning algorithms to analyze vast amounts of data – everything from purchase history and browsing behavior to customer reviews and social media interactions. Upon processing this data, the algorithms create a map where customers (those who have opted-in, and anonymized, of course) and products are positioned based on the strength of their relationship, with proximity reflecting the degree of relevance, preference, and engagement between them. In short, it helps capture the essence of customer preferences in a mathematical representation.

This approach provides businesses with a deeper understanding of customer-product affinities. At Tiger Analytics, we partnered with a leading beauty retailer to design a system that captures the true essence of customer preferences by focusing on both customer and product nuances. It begins with a harmonized product taxonomy and sanitized product attributes, and incorporates curated customer data from transactions, interactions, and browsing behavior. Together, these elements create an accurate and comprehensive view of customer affinities, allowing businesses to tailor strategies with greater precision.

How does customer product affinity embedding transform business decisions?

Customer product affinity embedding enhances decision-making by capturing the multidimensional interactions between business efforts, customer activities, product characteristics, and broader macroeconomic conditions. Unlike conventional machine learning approaches, which typically focus on solving one problem at a time and require custom feature engineering, this method integrates diverse business signals. Traditional approaches often isolate and aggregate these signals, but they fail to explain the overall variance or underlying business causality, limiting their effectiveness.

Caption: Matrix factorization foundation for affinity matrix

By incorporating deeper insights into customer preferences and behaviors into business strategy, beauty retailers can unlock greater efficiency, relevance, and personalization across various touchpoints. Below are a few ways customer affinity embedding can bring tangible advantages:

• Hyper-Personalized Recommendations: Take, for instance, suggesting a hydrating toner to someone with a high affinity for high-coverage foundations, thereby providing them with relevant products that match their needs and preferences.
• Smart Product Substitutions: Sarah, a regular purchaser of the ‘Sunset Shimmer’ eyeshadow palette, gets a notification suggesting a substitute — ‘Ocean Breeze’, a cool-toned palette with hues she may also enjoy — when her favorite product is out of stock.
• Store Inventory Optimizations: Optimizing inventory levels by predicting demand based on customer affinity. Businesses can avoid stockouts for high-affinity products and minimize dead stock for low-affinity ones, leading to reduced costs and improved customer satisfaction.
• Personalized Search: Traditional search relies on keywords and filters. However, these methods often miss the nuances of the customer’s intent. For example, a search for “foundation” might be someone seeking full coverage, or someone wanting a lightweight, dewy finish. Affinity embedding helps bridge this gap, ensuring more relevant search results.
• Targeted Marketing Campaigns: Consider targeting millennials with a strong affinity for Korean beauty with social media campaigns showcasing the latest K-beauty trends.
• Data-Driven Product Development: If a significant customer segment shows a high affinity for vegan beauty products, but limited options are available, the brand can proactively develop a high-quality vegan makeup line to fill that gap in the market.
• Personalized Buying Journey: Picture a customer searching for false eyelashes on the app, and then being recommended complementary items like glue and party essentials. Additionally, the system can suggest popular shades previously chosen by customers with similar preferences, creating a seamless and personalized shopping experience.

These are just a few examples of how customer affinity embedding can enhance customer engagement and improve the overall shopping experience. Other use cases, such as Trip Mission Basket Builder, Dynamic Pricing/Discounting, and Subscription Box Optimization further demonstrate how this technology can revolutionize customer satisfaction and business efficiency.

Real-world impact of customer affinity embedding on sales and engagement

Customer affinity embedding is a multi-step process that converts customer data points into a mathematical representation that captures the strength of a customer’s relationship with various products.

Caption: Functional architecture

The same embedding features can be transformed into affinity ranks, which serve as inputs for downstream ML models to generate personalized recommendations and provide insights such as:

• Product Similarity
• Customer Similarity
• Customer Affinity to Products
• Product Substitutions

Through our collaboration, the beauty retailer experienced a 4.5% increase in repeat purchases over a 12-month period. Additionally, the brand saw a 3.5% average boost in customer engagement scores within the fashion category, and a 7.8% rise in app usage. The company’s ROI for marketing campaigns also improved, with a 23-basis-point increase across digital channels.

Today, the real question isn’t just ‘what does the customer want?’ – it’s ‘how can we truly understand and deliver it?’

Understanding customer needs isn’t just about analyzing past behaviors, but rather predicting intent and adapting in real time. Customers don’t always explicitly state their preferences. Their choices are shaped by trends, context, and discovery. The challenge for brands is to move from reactive insights to proactive personalization, ensuring that every recommendation, search result, and marketing touchpoint feels intuitive rather than intrusive.

Customer product affinity embedding brings brands closer to the customer by placing the consumer at the heart of every decision. With data-driven customer understanding, brands can build deeper and more personalized connections, driving loyalty and growth.

References:

https://shop.nielseniq.com/product/global-state-of-beauty-2025/
https://www.gcimagazine.com/brands-products/skin-care/news/22916897/2024s-global-beauty-sales-are-powered-by-an-ecommerce-social-selling-boom/

The post AI in Beauty: Decoding Customer Preferences with the Power of Affinity Embeddings appeared first on Tiger Analytics.

Given the relatively weak presence of large retail chains in emerging markets (as opposed to the developed economies, where they are either dominant or at least have a much more formidable presence), the issue of assessing, on a continuous basis, the performance of the sales teams and taking action to maintain or improve the same is of paramount importance. In fact, not just in emerging markets – a lot of these apply even in developed markets where the trend is toward CPGs driving store-level decisions in collaboration with retail partners. This is a clear shift from a past that mostly dealt at a channel x national level.

Despite the critical role of the sales force, we have observed that outlet level/salesperson level measurement & insights and using that to improve performance and effectiveness isn’t that common or consistent, resulting in lost opportunities (visible manifestations being empty shelves, obsolete stock, and lack of ‘right’ choices for consumers at the point of consumption – all with associated financial impact for the brands).

In our experience, making a simple start by:

a) Tying in data across three specific areas (detailed below) – all within sales, and analyzing them to understand key levers that impact performance (vs hundreds of metrics/reports), and

b) Leveraging predictive analytics to discover headroom for growth at the right level of granularity to be actionable, often delivers a disproportionate impact vs effort spent.

Sales leaders already look at the following:

1. Sales force effort – attendance, hours spent, outlets visited, etc.

2. Compliance tracking – Right prices, promotion compliance, digital recording of orders

3. Results – achievement of targets, brand coverage, effective distribution

While a lot of metrics and reports are created out of such data to help make decisions on a regular basis, there’s a lot more that can be done with the same data and infrastructure to better assess the pain points and help the teams do an even better job.

1. Optimizing the Sales Leadership’s Bandwidth and Use it to Create Maximum Impact

The first and possibly the most powerful way to help the sales team is by helping the sales leadership prioritize efforts and budgets toward the biggest and most easily/quickly addressable problems. This can be done through analytic models that establish a link between performance (either sales goal based or a customized composite performance metric) to the most important drivers of that performance from the hundreds of activity metrics that are tracked.

The models can then score prospectively and identify potential locations that need attention to avoid slip-ups in achieving overall goals. This has been found to be immensely useful as it helps leadership adjust the right levers to drive impact on sales.

2. Help Sell the Right Products to each Outlet

A product/SKU recommendation engine integrated with outlet-order taking mobile app, built using AI-based advanced algorithms will help streamline the selling process and free up the salesperson’s time to focus on priority items such as selling focus SKUs as well as merchandising opportunities.

3. Assess Outlet Level Potential for Purchase, Stocking and Merchandising

Each retailer outlet has a unique capacity and appetite for stocking and selling different product categories as well as an affinity for certain types of promotions. Understanding this through their purchase history as well as those of similar retailers in the neighborhood, AI-based algorithms can provide real-time recommendations on the optimal type and amount of selling effort for each outlet.

4. Prioritize/Sequence Outlet Visits through the Day and Week

Different outlets and their handlers/managers, especially in the emerging markets, have different times of the day and days of the week when they are most open to salesmen visits as well as their sales spiels. Optimization algorithms can be developed to generate the most productive weekly/fortnightly route plan for the sales team to get the biggest bang for their efforts.

5. Design and Implement Targeted Consumer and Trade Offers (CO/TO) Based on Retailer Characteristics

CPG companies frequently roll out different promotions aimed at either boosting secondary sales (retailer purchases) or the consumer offtake (tertiary sales). These typically tend to be blanket promotions applicable to most outlets that their distributors cover, with only the occasional differentiation between wholesale and retail.

In reality, there are many different retailer groups out there looking for different incentives/rewards from the manufacturers. Understanding what these are and using sophisticated retailer segmentation solutions combined with AI-generated smart custom trade/consumer promotion plans can help give the retailers and consumers what they want, detect and prevent misuse of trade discounts, and improve the ROI on promotion budgets.

These are just a few ways to help CPG sales teams, but a great starting point, with the data already available with the organizations.

Does your sales force have the power of such insights helping them drive growth?

The post Unleash the Force of Sales: How CPG Teams Can Thrive appeared first on Tiger Analytics.

The clear, permanent shift towards digitally driven consumption is turning up the heat on retail, but for CPG manufacturers it represents an opportunity – at least till now, should we say? Ecommerce platforms are in fact fast becoming the main growth area for CPG companies, across geographies. (For some interesting statistics, we recommend reading this insightful article from Nielsen).

To win, CPG manufacturers adopt one of the following eCommerce models:

1. Partnerships with pure-play online retailers, of which Amazon has been a prime example (pun!?). While it is predominantly online, it is no more pure-play online only.

2. Online channels of traditional brick-and-mortar players (the walmart.coms of the world)

3. Direct-to-Consumer platforms with a content + commerce angle. Till now, this model is used more for content sharing with consumers than commerce – less than 1% sales across most categories, but this could change as CPG supply chains adapt.

Across all three of the above, especially on the commerce part, levers to win (as articulated in the pictorial below) are not very different from what worked in the pure offline world. Given our experience is mostly around delivering insights through data & analytics, the rest of this article is focused on that aspect.

Importance of eCommerce Data for CPG Manufacturers

In the offline world, CPG manufacturers get a broader market picture (volume/value sales, brand shares etc.) relying on data from syndicated providers (largely Nielsen & IRI) than having to pipe in PoS data* from every major retailer. We often hear in discussions that for the ecommerce side of the market, syndicated data sources are yet to fully mature to provide a reliable market view covering all relevant ecommerce players across the range of key categories. Given this context, an absence of any proactive data initiative by a CPG manufacturer will make it difficult to understand its brand/category growth drivers at the right level of granularity and use that to improve share. Striking the right data sharing partnerships with relevant ecommerce partners to get sales data in place and subsequently leveraging that for a range of insights-driven in-channel / cross-channel decisions is a high priority area for many top CPG companies.

[* Of course, CPGs leverage PoS as well, for account specific deep-dive insights and service level improvements, another trend that’s accelerated from around 2010 with the advent of affordable solutions to store and analyze data]

In an ideal state, marketing data – across traditional as well digital marketing channels, are brought in to comprehensively cover the ‘stimuli’ side, while sales data – shipments as well as data on consumption through ecommerce, PoS, syndicated, are brought in for a holistic picture of the ‘response’. Then there are others such as panel data, shopper cards etc. However, given such a large scope could take many years to materialize, CPGs often divide and conquer. When it comes to bringing large quantities of data in-house, or on to a platform managed by a partner on behalf of the CPG manufacturer, the scope of data that is brought in as well as the underlying technology infrastructure scales asymmetrically across functional areas, depending on:

1. Cost and ease of availability of data,

2. Ease of bringing the data on to internal platforms,

3. Utility of such data in relevant areas of decision making, and

4. Business value potential

These together drive the allocation of funds from the functions. In such a model, we have often seen acquiring data from ecommerce partners getting a higher priority over bringing highly granular data around digital consumer journeys which could be understood to a reasonable extent via agency provided solutions rather than bringing all marketing data in, on priority.

[Please note this is more of a sequencing decision than a substitute forever. Some of the respected global CPGs we work with already have a good hold on the marketing side of the data and are now moving to conquer the eCommerce side; but if you are just about starting on the data journey, the sequencing would be different, in our point of view. If not immediately, very soon, bringing comprehensive digital consumer journey data will become highly relevant to bring in rather than only rely on external inputs – if a CPG manufacturer’s aspiration is to be a category leader driven by differentiated insights. That’s another topic for a different day: back to ecommerce now]

Data Management

When it comes to building a solid data foundation for ecommerce, it is essential for CPGs to have the following covered:

Scope of data: Building out the overall strategy for data management requires scoping out data needed to align with business objective and availability. Data acquired from partner retailer includes ecommerce Point of Sales data, content & online behavior, and search terms. Internal firm data could be integrated with aggregated sales to provide a holistic picture. It could include promotion calendar, shipments specific to ecommerce, priority search terms, pricing strategy (ceiling/floor) etc.

Building robust data pipeline & quality control: It is crucial to build a scalable data pipeline. This includes collecting data from different sources, storing the data – including in-memory processing & storage, in an optimal way so that the data mining is effective and less time-consuming.

Data cataloging: Creating standardized metadata and ability to look up with master data is another critical element to ensure roll-up from individual components of data from various sources/geographies.

Governance: Establishing processes for data visibility (to users), data lifecycle management, aligned data aggregation rules vs arbitrary, and data quality monitoring to ensure effective data management

Covering these will ensure trusted & timely delivery of data to users. In summary, it is critical for CPG manufacturers to build expertise in eCommerce data management to ensure adequate data assets are available for the downstream analytics – whether such analyses are heavyweight predictive analytics by data scientists or lightweight DIY analyses by business users.

eCommerce Analytics

After* successfully building the data foundation, the next step is to arm the business with precise insights that drive differentiated execution. Yes, but in which areas? As outlined above, the other three critical pieces to win in eCommerce are Content& Communications, (R)etailer Partnerships, and Pricing & Promotions.

[*While the mention of analytics ‘after’ data may indicate the progress from data to analytics is very linear, most analytic themes are often tested for value using snippets of data even as the data foundation is taking shape and are quickly scaled across customer teams when a critical mass of data is in place.]

Analytics Around Content

Analytics is useful to optimize content and syndicate it across e-retailers. Causation analysis of product sales with product information is critical to not only optimize the content but also adapt to ever-changing needs for digital engagement. With deeper data from partners, the impact of product imagery and messaging on ecommerce sales is doable too, but not that prevalent as yet.

Partner-specific Analytics

A long tail of products is commonly observed in ecommerce where shelf space is unlimited. One of the struggles for CPG manufacturers is to understand their most profitable products and optimize its assortment for adequate coverage of consumer segments and price points for each retail partner.

If some form of consumer profile data (even aggregated) is available from the partner, that’s of great help. Even if not, classic price-ladders and blended data analyses with online purchase behavior from consumer panel providing a view of the preferences help make a start.

Another big area here is around service levels on shipments against ecommerce orders – which is as critical for ecommerce as in the off-line world. A quote seen in a recent article from BCG best summarizes this – “Stockouts, bad enough in traditional retail, can be deadly to an online seller”. It couldn’t have been said better. We recommend reading it for a detailed treatment of how CPG supply chains are adapting in the context of the three different ecommerce models.

Price & Promotions

Effective promotions – the online equivalent of traditional trade promotions, however it is named and accounted for, is highly critical in ecommerce as well for multiple reasons. It’s often a top spend item for CPG brands. In addition, pricing and promotions are highly visible for shoppers and comparison engines alike. Hence, it pays (quite literally!) to understand ROI through detailed impact attribution of promotional activity – what worked, where, when and what’s the true incrementality vs share shift. With good quality ecommerce partner data, this is an area that can be addressed with sufficient confidence. Even if only marketing spends are available and not detailed consumer journeys, it is still possible to get a good picture of promotional impact.

Consumer Digital Journey

This, of course, is not about ecommerce alone, but an integrated view of data from both ecommerce and marketing. Depending on the depth of the data, it is quite possible to build the equivalent of a Market/Media Mix Analysis specifically focused on consumption through the ecommerce channel; or get a complete view of the digital consumer journey replete with attribution analysis.

Of course, for such deeper analysis, data on offline + online media consumption as well as category consumption is required, which comes from specialized players, at additional cost. This approach helps get a comprehensive omnichannel consumption view of the consumer than having to draw artificial offline/online boundaries. Given that, such intensive data acquisition decisions are usually not taken alone by ecommerce teams, but with a total consumption perspective in conjunction with brand marketing and consumer market insights (CMI) teams.

Conclusion

For a USD 10 billion-sized CPG business with a 1.5% annual growth, if most of that growth in next few years is expected to come from ecommerce, that means a USD 500 million business opportunity over the course of 3-4 years. No wonder then that this space attracts much of leadership attention. As opposed to a general approach of evaluating ROI on individual initiatives, when it comes to eCommerce, looking at this bigger picture has helped many in the industry to quickly move from planning to execution mode.

The post 2024 CPG E-Commerce Trends: AI and Personalization Take Center Stage appeared first on Tiger Analytics.