• prudsys RDE | Recommendation Engine für Dynamic Pricing & Preisoptimierung in Echtzeit

Dynamic Pricing

Intelligent pricing with the prudsys Realtime Decisioning Engine (prudsys RDE for short) in real time.

The price is the most effective turnover and sales lever in retail. When determining the optimal price-sales functions and price elasticity using conventional pricing methods, category managers are confronted with an unsolvable problem on a daily basis. The sheer variety of products in the range as well as an extremely volatile market environment make it impossible to calculate the optimal price of an item at any time, manually or based on rules.

The prudsys RDE is the first dynamic pricing tool to be able to find the best possible pricing in real time. The prudsys RDE is used to completely automatically adapt thousands of product prices to customer behavior as well as to the constantly changing market and company situation.

Prices in the store as well as online are calculated based on the consumer’s predicted price acceptance. This happens dynamically for each item at any time, taking relevant pricing factors into consideration. Competitor pricing is an important factor that affects pricing but one that is always evaluated in the context of the (regional) brand strength of the retailer.

Regardless of the sales channel, retailers using the prudsys RDE can carry out at least three innovative pricing scenarios, optimizing them to include the desired parameters such as sales, turnover and revenue.

1. Value-added pricing

Optimization of earnings, turnover and inventory

Method

Intelligent regression, cluster and decision tree algorithms predict consumer price acceptance in real time. Calculations are based on historical price-sales data, real-time click data and many other relevant pricing factors. The algorithm is targeted to optimize earnings, turnover and inventory.

Suitability

Value-added pricing applies especially to basic items. Consumers are less focussed on the price of these items and their competitive relevance is moderate. It is also ideal for optimizing inventory for seasonal and fresh items (waste optimization).

Application

Pricing is completely automatic, not personalized and occurs across all common sales channels: offline, online, via e-mail and using mobile devices. The frequency of the automated price updates can be set as desired, from several times a week to weekly. Prices are optimized in accordance with rounding rules and in the specified price corridor with regard to the specified target function.

2. Strategic pricing

Optimization of sales, purchase frequency, market share and price image

Method

Intelligent regression, cluster and decision tree algorithms predict consumer price acceptance in real time. Calculations are based on historical price-sales data, real-time transaction data and many other relevant pricing factors. The competitor’s price takes on special significance in strategic pricing. It is weighted more heavily than value-added pricing but conversion to the competitor’s price is not 1:1. It is always evaluated in the context of the (regional) brand strength of the retailer. This helps prevent disastrous price spirals. The algorithms are targeted to optimize sales quantity, purchase frequency, market share and price image.

Suitability

Strategic pricing (or competitive pricing) is used for price focus and base price items in particular. These are items whose prices are familiar to consumers and where competitive relevance is high.

Application

Pricing is fully or partially automated, not personalized and occurs across all common sales channels: offline, online, via e-mail and using mobile devices. The frequency of the price updates can be set as desired, from several times a week to weekly. Prices are optimized in accordance with rounding rules and in the specified price corridor with regard to the specified target function.

3. Intelligent Couponing

Optimization of turnover and earnings as well as maximization of customer value

Method

Unlike value-added pricing and strategic pricing, intelligent couponing scenarios are implemented here. Above and beyond determining global profit relationships, this also requires the analysis of individual customer preferences and reliable prediction of customer behavior. Based on global price elasticity, intelligent decision models calculate individual customer preferences and generate predictions about purchase probability. These behavioral predictions can be taken from current customer behavior, historical transaction data or geo data. This way, consumers receive individually relevant product recommendations and individual discounts in real time. It is not a personalized base price that is calculated but rather the amount of the discount is individualized to provide incentive to customers. The algorithms are targeted to achieve customer loyalty, maximize customer value and for cross-selling and up-selling.

Suitability

Individual couponing is especially used to win over A-clients. These clients exhibit higher purchase frequency and generate more expensive shopping baskets.

Application

Thanks to the combination of personalized product recommendations and individual coupons, customers are rewarded with discounts on products that are relevant to them. Individualized coupons created automatically in customer newsletters, mass mailings and mobile apps are particularly useful ways of implementing intelligent couponing. Personalized discounts can also be generated as part of check-out couponing on the receipt, using customer loyalty cards or by way of in-store kiosk systems.

Whitepaper Dynamic Pricing

If you wish to dive deeper into the topic of dynamic prizing, we recommend our free whitepaper to you. Find out what you as a retailer may gain by using dynamic prize optimization and which retail use cases are promising. The whitepaper also explains the technical basics of dynamic pricing and addresses central issues of customer protection.

prudsys RDE | Recommendation Engine für Dynamic Pricing & Preisoptimierung in Echtzeit

Case studies

Dynamic pricing allows our clients to automatically adapt their product prices to constantly changing market and customer behavior in real time. Combined with personalized recommendations, there are numerous exciting applications for omnichannel personalization in retail. Our case studies will give you an idea about how our clients integrate real-time personalization into their business models.

Case Studies und Best Practice Beispiele für Omnichannel-Personalisierung mit der prudsys RDE Recommendation Engine

Expert knowledge

How does successful omni-channel personalization work? Innovative methods and algorithms form the basis of a personalized sales approach at the right time and via the perfect channel. The prudsys research and development team works constantly on future-proof real-time solutions to maximize customer value. Under the “Knowledge” tab you will find valuable background information about how the prudsys RDE works. Our media center boasts interesting contributions and explanatory videos.

prudsys RDE, Wissen, Technologie, Verfahren, Realtime, Analytics, Personalisierung, Personalization, Big Data, Data-Mining

Your contact

Jan Lippert - Director Sales & Authorized Officer - Vertriebsleiter, prudsys RDE, Recommendations, Omnichannel, Handel, E-Commerce

Jan Lippert

Director Sales & Authorized Officer
Phone: +49 371 27093-44
Email: moc.sysdurp@treppil