Dynamic price optimization (also called dynamic pricing) means that you, the retailer, adapt your product prices on a regular basis using an algorithm based on current market need. Prices are then generated automatically or semi-automatically. Your pricing solution also observes all relevant context conditions including demand, stock and competitor’s prices and adapts your item prices to maximize the success of your pricing strategy.

Retailers use system-based, rule-based pricing based on so-called rule engines as a precursor to intelligent pricing. The rule engines statically implement established pricing rules. For example, they set the price based on current competitor prices plus or minus x percent. However, the rules are firm and do not adapt intelligently to changes in the context conditions. They also provide no basis for active pricing and instead react only to external factors such as the competitor’s price. Of course, that can easily lead to price distortions when retailers are constantly underbidding or overbidding each other.

Rule engines are a precursor to intelligent pricing. However, growing product ranges and the increasing speed of market changes mean that rule engines are quickly overwhelmed.

Price elasticity indicates how demand for an item changes when the price varies. It may be derived from the price-sales function.

prudsys enriches the calculation with further factors, which are relevant for each article, e.g. competitor’s prices, relevant attributes of the article as well as real-time and historic transaction and sales data. The prudsys pricing solutions calculate complex sales functions for each item and at any given time (keyword: real time). Intelligent algorithms then derive the price which is most in line with the market at that actual time.

You can read about the factors that influence price and sales under the key word pricing factors.

You will have the most success with dynamic price optimization if you have defined a differentiated pricing strategy that defines and prioritizes exact target KPIs both globally and for the various item groups. Based on your KPIs we select the algorithms to optimize your prices. Of course, during implementation the KPIs serve as parameters for the success of the pricing method.

We would be pleased to assist you with strategy development. We analyze your historical sales data, calculate the complex sales function of your items, define common item groups and analyze the extent of the contribution individual items make to your turnover and earnings.

A personalized coupon is a customer-specific discount calculated by the self-learning decisioning model of the prudsys RDE on the basis of the sales function. Intelligent couponing, that relies on artificial intelligence (AI), is increasingly the method of choice when it comes to increasing purchase frequency and customer retention.

Why? Static discounts and coupons as we still frequently find in our mailboxes result in customers becoming habituated and reducing your earnings. For example, with such coupons and discounts, even customers who would have bought without the discount still get a discount or they get a (too) high discount even when they would have purchased at a lower discount. The goal, therefore, is to use your resources more strategically while keeping an eye on your margin.

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 in the form of self-learning algorithms comes into play. These algorithms calculate the optimal price completely automatically for any item at any time. 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.