Background: Artificial Intelligence for Retail

We compiled background information on artificial intelligence (AI) in retail for you. We explain central concepts and approaches and how they are connected to our AI-based personalization and pricing solutions.

Terms used: What terms do we, and others, use?

Authors in different languages make use of a variety of synonyms but the English term artificial intelligence, abbreviated to AI, is widely accepted in scientific literature. We also use the terms algorithms and agents (less common) synonymously.

How do we define artificial intelligence (AI)?

There is no “official” definition for AI. Artificial intelligence supports people when they are working with large volumes of data that feature complex relationships. This data needs to be analyzed quickly before decisions can be made on the basis of that analysis.

An essential feature of any AI is that it is able to learn. Initially “the machine” learns with training data before generalizing its knowledge and applying it to unknown data (keyword: machine learning). Datasets change very quickly these days and “the machine” learns from every new dataset that it processes (keyword: incremental or adaptive learning).

To optimize the quality of its knowledge, “the machine” continuously evaluates the quality of its decisions. It receives a “reward” for every “good” action in line with the final goal, learning to maximize the benefit of the overall system (keywords: reinforcement learning and network chain optimization).

See below for more on machine and reinforcement learning.

In any case, it is people involved in our personalization and pricing solutions who define the rules by which the AI makes decisions. People set the target parameters for the optimization of the system as a whole. Both the area of application and objective necessitate careful selection and the combination of perfectly compatible algorithms. When contextual conditions change, our intelligent agents flexibly adapt their behavior in real time.

You can read about other, sometimes controversial, definitions and approaches in our blog article entitled „Künstliche Intelligenz: Von der Nischentechnologie zum Hype“ (in German).

What are the strengths of AI?

Good decisions: Our intelligent algorithms always provide you with the best decisions, giving you valuable competitive advantages in a highly dynamic market. Depending on the area of application and strategic objective, we combine suitable algorithms to best optimize the target figure.

Real time: Our personalization and pricing solutions constantly analyze all relevant contextual conditions including customer behavior, inventory and competitor prices, adapting their behavior to changes in real time.

Speed: Our personalization and pricing solutions are high-performance solutions that can process even huge volumes of data in an average of 0.025 seconds. By way of comparison: it takes 0.1 seconds to blink.

Automation: The AI used in our personalization and pricing solutions calculates and generates recommendations and prices. “The machine” analyzes huge amounts of data and manages computations of which humans are no longer capable. Humans are not being replaced but instead they are constantly being asked to stake out the framework for the AI by implementing their ideas, concepts, knowledge and morals. Humans determine the strategy and the target parameter to be optimized. They stake out the corridor for action for the AI.

What do chess and AI have in common?

We often compare the way AI works in our personalization and pricing solutions to the way a chess computer works: The computer recognizes the “moves” of the customer, anticipates the chain of all possible next “moves” and develops its own actions (e.g. product recommendations) so that it wins “the game” (e.g. the target parameter of customer value – not only short-term sales maximization). Granted that greatly simplifies the situation but it also paints a picture of AI that even the layperson can understand. We would like to emphasize in particular the long-term optimization of the target parameter of Customer Lifetime Value across the entire customer journey (keyword: network chain optimization).

More on Artificial Intelligence

Machine and reinforcement learning

From a historical perspective, the development of our AI technology started with data mining. Along with the availability of large volumes of data came the desire to analyze ever larger datasets (keyword: big data), recognize patterns and use this knowledge profitably. Data mining continued to develop in the direction of machine learning, which far exceeds simple pattern recognition in datasets.

Following the learning phase, “the machine” generalizes its knowledge and is then able to apply it to unknown data. In the beginning “the machine” learned only from static datasets but there was soon a need to learn adaptively (or incrementally). When it comes to adaptive machine learning, “the machine” learns from every new dataset that it processes. There are considerable advantages to this when it comes to both speed (keyword: real time) and quality.

The latter improves even further if “the machine” also receives a reward for every “good” action. We refer to that as reinforced learning, learning through rewards and punishment or reinforcement learning. “The machine” learns how to act in potentially occurring situations in order to maximize the benefit of the overall system towards a target parameter over the long term (keyword: network chain optimization).

For “the machine” to remain flexible and to prevent a “filter bubble” from occurring, it can deviate from the learned patterns through so-called exploit and explore mechanisms, e.g. to recommend products or content that have not been recommended for a long time or have never been recommended. The AI ensures that its scope of learning and action remains flexible by trying out alternatives or new variants.

What role does AI play in omnichannel personalization?

It is no longer possible to manually manage a customized approach to each individual customer via every channel with the “perfect” offer that corresponds to the customer’s current shopping behavior, is in stock or is available in the customer’s desired store. This is where artificial intelligence (AI) in the form of self-learning algorithms comes into play.

Our personalization solution learns personalization rules (keyword: adaptive learning) automatically and in real time – e.g. on the basis of clicks, shopping carts, purchases, external and internal search queries, clicked categories and banners or even selected events. The AI-based software collects all of this data independently and continuously. In addition, the algorithms measure the acceptance of the generated content (keyword: reinforcement learning). If a generated recommendation is accepted by the customer, the system rewards itself. If the recommendation is not accepted, there is no reward. This is how the recommendation engine learns gradually and can better cater to each individual user in a more targeted way with each interaction.

Translated to retail, this means that if you use an algorithm that works according to the principle of reinforcement learning, you will be able to maximize the benefit of your “whole system” over the long term – in other words, the crucial variables such as sales, turnover and profit.

If you would like to learn more about personalization, we recommend our page entitled What is personalization.

What role does AI play in dynamic price optimization?

In an age of big data, digitalization and a highly dynamic market, it is no longer possible for humans to adequately control the variety of influencing factors on the price. This is where artificial intelligence (AI) in the form of self-learning algorithms comes into play. These algorithms calculate the optimal price completely automatically for any item at any time. However, that doesn’t mean that your prices change on a second by second basis. You determine the frequency of the price adaptations for your sales channels. Thanks to real-time calculation, you always have the optimal price for your products when you adapt your prices.

The AI takes over the calculation: What is the fair market price of an item taking into account all of the pricing factors as regards optimizing your KPIs? Your category management sets the framework and dictates to the algorithms what to do.

If you would like to learn more about dynamic price optimization, we recommend our page entitled What is price optimization.

Why is prudsys a specialist in AI for retail?

Jens Scholz, founder and current CEO of prudsys AG, said it best in an interview written up in our blog: “prudsys AG has been involved with artificial intelligence and the automation of decisions since its founding. […] We found the challenge of measuring data in real time, learning directly from that and being able to play back the results in real time to be particularly exhilarating.”

We have been involved with the topics of machine learning and reinforcement learning, and later with AI, since as far back as 1998. At the time, a group of math and computer science students at the Chemnitz University of Technology decided to apply the theoretical knowledge they had learned in data mining to practice (among them our founders Jens Scholz and Dr. Michael Thess). Over time they figured out the appropriate field of application for data mining – the retail industry. They used new ideas to find opportunities to automate and optimize processes, allowing them to follow today’s vision.

Our goal is to use AI to simplify life for retailers and consumers so that both sides experience an unprecedented gain in productivity and convenience. At the same time we would like to make a meaningful contribution with our ideas. Whether its curbing food waste in grocery retailing by way of markdowns or reducing the use of paper through personalized catalogs we are constantly working on future scenarios for the retail market with new AI services.

prudsys has 15 years of experience in the application and further development of machine and reinforcement learning. We employ specialists to work on our Data Science Team in both Chemnitz and Berlin who are constantly researching innovative methods and continually optimizing our AI. We are the market and technology leader for real-time personalization and dynamic pricing in omnichannel retail.

Where can I learn more about AI for retail?

Arrange your personal web session on the subject of AI in retail today. Our experts will be happy to explain to you more about the potential you can exploit with AI.