4.5%
uplift in gross profit after 8 weeks
4.5% uplift in gross profit after using Competera's demand-based engine
Omnichannel electronics giant sees 4% growth in key business indicators from price recommendations suggested by Neural Networks.
Our client is one of the leading Eastern European retailers in the consumer electronics sector. With a versatile range of products, the retailer sought to optimize its pricing process, and as a result, to increase the margin. And do it using the portfolio pricing strategy. After implementing Competera's bespoke deep learning algorithms for price recommendations, the client was able to achieve several key business objectives, including a 4.5% uplift in gross profit.
4.4%
increase in total revenue of the test category
42 000
applied price recommendations during PoC
The challenge
Since our client is the #1 consumer electronics retailer in their country, the assortment of their categories can be described as a variety of brands of any model, color, or shape. Managing over 3 billion dollars yearly revenue, the pricing team was motivated to streamline all their pricing processes.
Due to the high number of similar goods available on the market, price changes for similar products of direct competitors affected client sales more than changes in their own prices.
Every pricing decision had to take into account cross-impact dependencies with different reactions of demand to price changes.
The client faced sales changes within the portfolio from more profitable to less profitable products.
The need for frequent repricing of large quantities of SKUs.
The Solution
To meet these challenges, our pricing architecture team suggested using a demand-driven pricing engine powered by Neural networks. It considers price elasticity of demand, cross-elasticity, competitive environment, and other crucial factors to recommend optimal prices. Historical data collected throughout 2.5 years was taken as a foundation for calculation and design of ML algorithms.
Execution
The whole work process can be conventionally broken down into several independent milestones.
The PoC Design
The project's success was determined by the growth of the target metric, the gross margin. Using algorithmic pricing from Competera, the client expected to see the metric grow by 5% or more.
Revenue retention was chosen as the metric to protect. The algorithms had to automatically take into account the client's existing pricing rules and recommend changes only to shelf prices.
For the Proof of concept launch, we chose a method of comparing the test and control groups across two different regions with similar sales histories and customer behavior.
The fine tuning (key learnings)
If you are preparing to implement such a solution in your business, pay attention to the quality of the input data. During the current project, we discovered several important learnings.
- ML algorithms can round prices in accordance with business rules, but this may significantly affect products with low price elasticity.
- Ignoring systematic returns and promo mechanics leads to inaccurate forecasts and a drop in the target metric.
The implementation
Full deployment of the optimal price recommendation platform goes through a multi-stage process.
- 1
Set project goals
- 2
Integrate, set and check continuous data flow
- 3
Training of ML models
- 4
Use price recommendations for one test category
- 5
Process debugging and model improvement
- 6
Scaling
Results
Of course, these are just a few options suggested for specific products and specific situations. If you look at the overall picture, our work with each SKU separately and in relation to each other showed cumulative growth in general. Thus, the growth of the two targets was 4.4% in revenue and 4.5% in gross margin.
While finding optimal price points across the range, our algorithms mostly make two types of decisions. The first situation is when a product's demand is elastic to its price. It reacts well when price decreases and badly when price increases. This situation is quite typical for the economy price segment.
Typically, algorithms recommend decreasing prices after facing such behavior. You can see the reaction on the charts below.
These basic headphones belong to the medium price segment. Two recommendations to reduce prices resulted in revenue growth both times.
After implementation, the algorithm recommended decreasing a price that category managers had not revised for a long time, which led to growth in revenue and sales.
Let's consider the second frequent type of situation when the product reacts well to a price increase. In such a case, an algorithm would recommend setting a higher price. We will observe an increase in profit without a fall in revenue.
After the headset price was increased, revenue did not fall and gross profit grew by up to 15% versus the lower-price period.
For these studio headphones, the algorithm adjusted prices up and down. The first recommendation preserved revenue and increased profit, while the later decrease accelerated revenue growth.
Today, portfolio optimization and artificial intelligence are still fighting for retailers' trust. However, proper teamwork and trust in each other lead to incredible results, as this case shows. I think that close collaboration between the teams is a major part of the success of implementing innovations in modern retailing.
Alexandr GalkinCEO of Competera
Competera Pricing Platform helps retailers to craft optimal offers
Discover how Competera helped other retailers to thrive
