How a Major European Retailer Takes Personalized Online Shopping to the Next Level with FindTuner

At Innovent, we spend a lot of time thinking about how machine learning can improve online shopping experiences by helping retailers deliver highly personalized results to their customers. But because we’re not in the retail business ourselves, we don’t get to see the impact of our FindTuner technology firsthand.

 

That’s why we relish the opportunity to talk to retailers who benefit from our solutions – as we recently did when I sat down with Gautier Schaffter, senior product manager at Migros Specialized Markets, to discuss how his company leverages FindTuner to improve the impact of product searches.

 

Keep reading for a look at our conversation, which highlights how Migros, one of the largest retailers in Switzerland, is applying machine learning to take customer personalization to the next level by delivering highly targeted and ultra-relevant results – something that conventional search algorithms just can’t do.

 

Tell us about Migros Specialized Markets’s core business and its overarching tech strategy as it pertains to product search.

 

Migros Specialized Markets (MFM AG) focuses on the non-food segments of Migros, one of the largest retail companies in Switzerland. Our core business is to provide a wide range of high-quality products to our customers at affordable prices, while also maintaining a strong commitment to sustainability and social responsibility. MFM AG is composed of five brands (Melectronics, Micasa, SportX, Do It + Garden and Bike World), each with their own brick-and-mortar as well as online stores.

 

In terms of our overarching tech strategy, we strive to leverage technology to enhance the overall shopping experience for our customers. This includes providing a seamless and intuitive online shopping experience through our e-commerce platforms, as well as improving the in-store experience through various digital initiatives.

 

As it pertains to product search, we recognize that search is a critical component of the online shopping experience. Therefore, our tech strategy in this area focuses on delivering relevant and personalized search results to our customers. We do this by leveraging various data sources and machine learning algorithms to understand customer needs and preferences, and then surface the most relevant products accordingly. Additionally, we continuously iterate on our search algorithms to improve their accuracy and relevance over time.

 

 

In which areas or categories of MFM AG’s shopping sites is it using technology from Innovent?

Our e-commerce platform uses FindTuner to improve search results, sorting relevance, and some merchandising features on our shopping sites. This approach is in line with our overarching tech strategy to leverage technology to enhance the overall shopping experience for our customers. By using Innovent’s technology, we are able to continuously iterate on our search experience and sorting relevance to improve their accuracy over time.

 

Overall, our partnership with Innovent has helped us to deliver a more personalized and relevant shopping experience to our customers, which is a key priority for us.

 

Why was Innovent chosen and how exactly is MFM AG using Innovent technology?

We were originally looking for a partner that could help us improve our search configuration and Innovent’s experience and track record in these areas made them a natural choice. After a few rounds of optimizations, we decided to implement their FindTuner extension to push our merchandising and search optimization capabilities further.

 

Why did MFM AG decide to embrace machine learning? What was the driver for the decision?

MFM AG embraced machine learning as a means of enhancing the overall shopping experience for our customers. Machine learning enables us to gain a deeper understanding of customer intent and preferences.

 

An additional driver for our decision to embrace machine learning was the growing volume of data available to us through our e-commerce platforms. With more and more customers shopping online, we had access to a wealth of data on customer behavior and preferences that we could leverage to deliver a more relevant experience.

 

What benefit is machine learning adding to users’ experience? How tangible are the benefits of personalization and dynamic search optimization and what data exists to quantify those benefits?

 

Machine learning is adding significant benefits to our shopping experience by enabling us to deliver more personalized and relevant search results, sorting relevance, and merchandising features on our shopping sites.

 

One of the most important benefits of machine learning is that it allows us to better understand customer intent and preferences. By analyzing customer search queries and behavior, we can gain insights into what products customers are looking for. We then surface the most relevant products and merchandising features, which in turn drives increased engagement and conversion rates.

 

Another benefit of machine learning is that it allows us to continuously iterate on our search algorithms and sorting relevance to improve their accuracy and relevance over time. This means that the more customers use our platform, the better it becomes at delivering personalized and relevant search results. This leads to a virtuous cycle of increased engagement and customer satisfaction.

 

The benefits of personalization and dynamic search optimization can be quantified through a variety of metrics, including engagement rates, conversion rates, as well as product click-through-rate.

 

Similarly, what’s gained by minimizing manual tuning of the experience? What does that bring to the table?

 

While it is important to have human experts involved in the tuning process, leveraging machine learning algorithms and automation tools like Innovent’s FindTuner allows us to use our resources more efficiently and focus on more important or complex cases that still require human input.

 

By reducing the amount of manual work required for search optimization, we are able to free up our experts to focus on more complex and high-impact cases. This helps us to improve the overall shopping experience for our customers, as we are able to devote more attention to improving key areas of our platform.

 

Overall, the technology provided by Innovent has allowed us to optimize our search experience more efficiently, reduce the amount of manual work required, and focus on higher-impact cases that require expert attention.

 

How does the process work? Could you differentiate the ML process for us from something like the Amazon algorithm? Has it changed the way that the day-to-day reality of Migros Specialized Markets works?

 

The process of using machine learning for product search involves several key steps. First, we collect anonymized behavior data including search queries and click data as well as product performance. This data is then used to train machine learning algorithms to understand customer intent and surface the most relevant products accordingly.

 

In terms of day-to-day reality, using machine learning for product search has certainly changed the way that we work at MFM AG. It has allowed us to provide a more personalized and relevant shopping experience for our customers, which is a key priority for us. However, it’s important to note that while machine learning has enabled us to improve the search experience, it is not a silver bullet solution. There is still a lot of work required to ensure that our models are properly trained, and we continue to rely on human experts to fine-tune the search experience and provide oversight to ensure that the results are accurate and relevant.

 

Overall, machine learning has been a valuable tool for enhancing the search experience at Migros Specialized Markets, but it is just one piece of a larger puzzle that includes human expertise, data collection, and ongoing iteration and optimization.

Talk to us about the potential of scalable merchandising in large catalogs. How are you leveraging that benefit? How does it enhance the customer experience?

 

Using scalable merchandising solutions allows data-based product recommendations, which can help improve the overall customer experience. For example, by taking a customer’s purchase history and browsing behavior into account, it is possible to suggest products that are likely to interest the customer, leading to increased customer satisfaction and loyalty.

 

Additionally, scalable merchandising helps manage the inventory more effectively by highlighting products that are selling well and predicting which products are likely to sell out.

 

Do you think machine learning and intensive personalization of the shopping experience are the wave of the future?

 

Definitely. Studies have shown that more and more users expect personalized experiences and relevant content. This allows customers to shop more efficiently and discover relevant products based on their preferences and behavior. Machine learning is the most effective way to effectively and efficiently leverage data to offer such experiences.

 

Would you like to share anything else that you feel is useful to give business readers insight into integrating ML into their business models?

 

Sure. Here are some key pointers based on our experience so far:

  1. Start small: Don’t try to implement machine learning across your entire business all at once. Start with a small project and build from there. This will help you to identify any issues or obstacles early on, and make it easier to scale up in the future.
  2. Focus on the customer: Machine learning is a tool to help you provide better customer experiences. Keep the customer at the center of your ML initiatives and focus on providing them with more personalized and relevant experiences.
  3. Get the right talent: Machine learning requires specialized skills, so it’s important to have the right talent on your team. Consider hiring data scientists, machine learning engineers, and other experts who can help you build and implement ML models.
  4. Invest in data quality: Machine learning models are only as good as the data they’re trained on. Make sure you have high-quality data that is relevant and up-to-date.
  5. Monitor and refine: Machine learning models are not set-and-forget solutions. You need to monitor their performance and refine them over time to ensure they continue to deliver value.

Conclusion

As Gautier’s experience highlights, truly standing out in the highly competitive world of online retail requires more than just standard product searches. Forward-thinking businesses need to take advantage of next-generation technologies that significantly enhance search tools’ ability to surface products that individual shoppers will find relevant and compelling.

At Innovent, we’re proud to be delivering those solutions to Migros and retailers like it across the globe.