Kesko: Leveraging Finland’s most extensive grocery data

In August 2023, Kesko, in a partnership with Futurice, launched the first version of the K-Hyvinvointi concept within its popular K-Ruoka application. By analyzing Plussa benefit card data, K-Hyvinvointi integrates customers’ details, dietary preferences, and goals into one nutrition index, guiding them toward healthier food options that are in line with national nutritional guidelines.

Developed in collaboration with renowned nutritionist Reijo Laatikainen from Lääkärikeskus Aava, K-Hyvinvointi is the first service to integrate dietary guidelines and recommendations directly into the digital consumer grocery shopping experience. It is designed with family healthy nutrition goals at its core, offering an easy and intuitive platform for improving nutritional well-being.

Rising food prices have significantly affected Finns’ shopping habits in recent years. The K-Barometer survey reveals that approximately 22% of consumers have shifted to less healthy eating patterns in response to rising costs. This trend is also reflected in Kesko’s sales data, showing an alarming decline when shopping for fruit and vegetables.

The K-Barometer survey highlights that about 78% of respondents who bought less healthy foods were conscious of the negative impact of their choices and concerned about the consequences. The survey also highlights another pressing issue: insufficient physical activity among the population, costing an estimated three billion euros in annual societal expenses.

In response, Kesko – recognized seven times as the world’s most responsible grocery store – is taking proactive steps. The company understands the importance of informing its customers about healthier dietary choices. The new feature aligns with Kesko’s commitment to addressing societal challenges and its dedication to promoting environmentally sustainable choices vital for overall wellness and health.

Kesko serves 1.2 million customers daily at K Group’s 1,200 grocery stores and holds Finland’s most comprehensive food-related database, the Plussa data. Kesko’s customers are highly active and over 3.3 million Finns use the Plussa card.

Globally, the public’s desire to understand overall well-being is growing and grocery shoppers especially are interested in knowing how their dietary choices impact their health. Kesko’s research points out conscious consumption as an emerging trend in dietary and nutritional habits. Simultaneously, there’s a growing awareness about data sharing and its implications, and Kesko understands that its customers are actively interested in using this data to improve their lives.

With a grander vision of supporting customers on their journey to greater well-being, Kesko recognized the need to initially focus on its biggest asset – its broad grocery database and active customer base.

The first K-Hyvinvointi concept started off as a service that seamlessly integrates the following key elements:

• Customers’ grocery shopping data
• Customers’ dietary and nutrient goals
• Kesko’s extensive product database
• Finland’s largest recipe collection
• National dietary guidelines

When the development of the K-Hyvinvointi service started in January 2023, Kesko’s AI team started by diving deeper into the nutritional analysis of its product database of over 100,000 items.

In partnership, Kesko and the Futurice teams collaborated closely with nutritionist Reijo Laatikainen and his team of experts at Lääkärikeskus Aava to improve the nutrition information of food items. The primary focus was the development of frameworks and models for more nuanced nutritional information and categorization. The team faced several challenges, such as determining how to build diet attributes – for example, initially, the idea of labeling a banana as a vegan item had not been considered in the database.

Another challenge of the project was to create a nutrition index. How do condense numerous recommendations and studies into a single, user-friendly format that allows users, often shopping in a hurry, to understand their nutritional status quickly? Or how to provide options for shoppers that are both appealing and healthy?

In the final product, the developed nutrition index shows each nutritional goal with a symbol and color, and a five-point scale provides an overview visualization of each category's status. At a glance, the user can see, for example, how the goal of eating more fish as a family unit is progressing. For product recommendations, the team used collaborative filtering ("customers who bought similar products to you also bought..."). This helps to find healthier options for the products that the customer is currently buying and which are still interesting to the customer.

Drawing on the data, the team recognized the importance of seasonality when searching for recipes. K-Hyvinvointi uses state-space models to analyze the seasonality, ensuring recipe recommendations are not only personalized but also remain relevant year-round, whether it’s summer or winter season.

The K-Hyvinvointi feature leverages the existing infrastructure of the K-Ruoka application, which automatically captures shopping data when a customer presents a Plussa card at the cash register. Supervised learning is employed to understand how the purchase history of a customer can be used to predict relevant recipes, allowing for the personalization of recipe recommendations to all customers. Upon activating the K-Hyvinvointi feature in the app, the user provides essential background information such as household size, personal diet preferences, nutritional goals, and food preferences.

The service aggregates purchase data from all household members who have linked their cards into one view, forming a basis for analyzing consumption across 12 food categories: Fruits and Berries, Seeds and Nuts, Legumes and Vegetable Proteins, Vegetables, Fish and Shellfish, Sugar, Cereal Products, Dairy Products, Eggs, Butter and Fats, Red Meat, and Salt.

The key element of the K-Hyvinvointi service is its easy onboarding, goal setting, and personalization. Goal setting is simplified upon feature activation, offering three automated options based on historical purchase data. The service also provides a possibility to select the goals the user feels are most relevant for them and their families. For those interested in more detailed information, background info on the national dietary goals and the studies behind them is easily available.

User experience was a critical aspect of the development. The goal was to create a seamless user interface for K-Hyvinvointi in an app that hosts multiple other features and information. The user testing group ensured the new feature was integrated smoothly into the K-Ruoka app. It evaluated how information was displayed, determining which details were important and which were less so. Simplifying the information was critical, aligning with Kesko’s insight that customers often face time constraints when doing their food shopping.

From a technical implementation perspective, the team used Python for data science, and the models are containerized in AWS. The results are served by an API, where the product and recipe recommendations are calculated in real time.

By leveraging AI and data, K-Hyvinvointi transforms its vast grocery database into a service that empowers customers to make better choices. Users are highly satisfied with the feature’s intuitive user experience and personalized shopping and recipe recommendations.

K-Hyvinvointi offers personally tailored recipe suggestions that are based on users’ purchase histories and diets. Recipes are neatly categorized, enabling users to easily find choices that match dietary needs – whether they're looking for vegetarian, vegan, lactose-free, milk-free, or gluten-free diets. If users want to customize their diet further, they can easily opt out of ingredients and foods they don’t like.

Moreover, the personal recommendations feature has attracted significant interest from users. It offers a Netflix-style carousel of suggestions, generating recommendations based on users’ food shopping data and assigned goals. Users can easily add recipe ingredients directly to the digital shopping basket. This approach makes achieving nutritional goals – both in terms of shopping for ingredients and preparing meals – efficient and enjoyable.

K-Hyvinvointi feature is now expanding to include calculations of vitamins and other nutrients based on customer purchase data. For instance, it can calculate the amount of vitamin A obtained from consuming one large carrot daily per person and suggest new recipes to improve vitamin A intake. The work for improving well-being and the development of better AI-driven tools for it continues.

The K-Ruoka app is available on Google Play and App Store.

Grand One entry details:

TYÖ: K-Hyvinvointi

ASIAKAS: Kesko

SUUNNITTELU: Kesko, Futurice, Aava, Qvik

TUOTANTO: Kesko, Futurice, Aava, Reaktor, Qvik, Nitor

KATEGORIAT: Paras datan käyttö, Paras AI:n tai muun uuden teknologian käyttö