Discover How Imprice Can Help You Achieve Your Business Goals
We will make a detailed demonstration of Imprice and use cases:

How artificial intelligence calculated optimal prices for e-commerce, increased gross profit by 20.1%, and reignited demand

August 17, 2020
Source: NEW-RETAIL MEDIA is a Russian retail chain and online store of sports nutrition. The company's consumers mostly are active visitors of Moscow or Saint Petersburg gyms, improving the training result with sports nutritional supplements and vitamins.

Due to the COVID-19 spring lockdown, gyms in Moscow and St. Petersburg were closed until July 2020. As a result, the company's offline stores were closed, and with non-worked gyms, online sales decreased almost to zero. AI-driven Imprice modules helped to reignite demand and accelerate the gross profit of the online store.
The business was booming before the spring lockdown
Evgeny Bernitsky
CEO at
Until the coronavirus spring, was in a perfect situation.

Since June 2019, we have implemented automated real-time repricing based on our competitors' prices. When competitors raised prices of some SKU, our price automatically increased to a target position. If competitors cut prices, our price followed them.

Imprice cloud platform made us all this magic, including collecting competitors' prices and automatically uploading actual prices to our stores and our website. We only occasionally improved pricing rules: changed marginality constraints and target price position - the second price at the market, third, fourth.

Automation of repricing based on competitors' data increased our gross profit by 16% in several months. LFL (Like for Like) growth was about 30%; margin level was satisfactory.
Rule-based Imprice modules implemented before lockdown in 2020:

competitive pricing,
zone pricing,
KVI pricing,
inventory turnover pricing.
Self-isolation and collapsed sales
Evgeny Bernitsky
CEO at
Then March 2020 came.
As soon as gyms had been closed, proteins and gainers sales dramatically decreased because people stopped strength training. Besides, our offline stores were closed.
The turnover dropped by 60%.

Due to currency rates changing, procurement of goods costs raised, and margins fell sharp. We were suffering severe losses, and in April, there was a feeling we could see the end of the company soon.

We still used automated repricing based on competitors' data, but there were no sales anymore. It seemed nobody at the market understood what prices could be optimal.

We decided to try a new pricing approach: ai-driven price optimization based on demand, not on competitors' offers.
In May 2020, tested an anti-crisis tool: Imprice ML-pricing module (ML - machine learning), based on demand sensing. The company launched a two-week pilot with one product category and saw gross margins raised impressive compared to the online shop and control category.

At the end of May 2020, entered the next phase of implementation and put prices of 80% of their assortment under AI management. AI-driven analytics modules helped to manage another 15% of SKUs.
Key results of AI-driven pricing implementation
The company compared sales data in June, when AI-algorithms managed prices, with sales in the previous month, May 2020.
Revenue growth
Gross margin growth
Number of online orders growth
Average Order Value growth
Essential fact:
In June, the sports nutrition market crisis remained: gyms in Moscow and St. Petersburg were still closed. Internet traffic in June even decreased compared to May.
Key implementation results for an online store, June to May 2020: though Internet traffic was still falling, revenue, profits, the number of orders, and Average Order Value increased.
You can find 20 additional indicators at the end of the article.

Let's explore the case's details and see how exactly AI-modules managed the prices.
Different pricing approaches for various assortment groups
Why did the company give AI-modules only 80% of SKUs' prices to manage, not the entire assortment? The reason was had goods segments with different price specifics.
5% of the assortment of the retailer were goods with the RRP (recommended retail price).
The segment contained popular brand items. Suppliers monitored the market and didn't allow lower prices below the recommended retail price, RRP.
Accordingly, these SKUs' prices were the same for all competitors: it was impossible to reduce them, and it was pointless to increase.

15% of the assortment were KVIs, those brought Gold-Standart 55% of sales.
The KVIs affect consumer price and assortment perception, drive traffic and sales. Most consumers tend to compare KVI prices in different stores.
Due to these facts, continued to use a competitor-based approach for KVIs' prices, but now with AI-algorithms determined the list of key competitors for each KVI precisely.

80% of the assortment were goods with regular properties.
There were goods from "foreground" and "background" groups, including items consumers stopped to buy during the COVID lockdown.
AI-pricing module started to set prices for all goods in that segment. A pricing specialist only monitored results but didn't manage the pricing process manually.

Automatic identification of key competitors
Evgeny Bernitsky
CEO at
We significantly improved identifying KVIs already in 2019.

First, we leveraged Imprice ML-module for recognizing all KVIs in our assortment. The algorithm identified 150 KVIs, whereas our employees only knew about 50 of these items.

Second, we set into the Imprice platform list of stores we considered our competitors. Imprice kept our price attractive compared with these retailers: every time, it took the lowest price among set competitors and made our price slightly higher, considering our margin restrictions.
That strategy helped us grow in both orders and profits.

In April 2020, sales of KVIs fell, like sales of other goods. Imprice experts offered us to check which stores were affecting, in fact, the sales of our KVIs: to whom the consumers went if they offered a better price. We launched an AI-driven Imprice module, "Automatic identification of key competitors.
"Key competitors" are stores that have a significant impact on sales. If a key competitor lowers the price, Gold-Standart customers go to him for purchase, so Gold-Standart's revenue reduces.

Often lists of key competitors for different items vary: one set of competitors affects some goods' sales, and another set influences others' sales.
Imprice analyzed past data over several months: sales, prices, competitors' prices, stocks, competitors' stocks, intersections with competitors in specific product categories and brands, periods competitors paid for top advertising positions and other competitive factors.
As a result, gained an accurate list of key competitors for each SKU.
Evgeny Bernitsky
CEO at
Imprice identified our key competitors. Surprisingly those were bad reputation stores with extremely low prices.

We provided consumers good-level consultations about assortment; we posted high-quality content on social networks; we sponsored sports events. It seemed that consumers had a high loyalty and recognized as a confident store with good service; we supposed our competitors were well-known large stores.

But in fact, our key competitors were online stores that:
processed 100 orders per day or less,
had a very narrow assortment and low-quality sites,
set the lowest price on the market and used price aggregators for advertising.
These stores "stole" sales of our KVIs.
The company adjusted pricing rules for KVI goods.
In 2019, the company's specialists prepared a list of "important competitors" relying on their experience and intuition. Pricing formulas considered those competitors' prices.
From May 2020, the company calculated prices already on data of key competitors identified by Imprice. The platform kept the second minimum position of KVIs prices among low-price small stores from a new list, not among large retailers as before.
Launching demand-based price optimization
The module "Automatic price optimization" calculates optimal prices by analyzing dozens of demand factors.
"Optimal" means, implementing that price configuration, a company achieves the maximum gross profit margin at the assortment level.
Machine learning algorithms evaluate goods' cross-impact and segment items by their roles in the consumers' basket: basket drivers, traffic drivers, profit drivers, complement goods, substitutes, and others.
Then each segment gets its optimal pricing strategy according to your business goals.
To launch ML Imprice algorithms, the company made three easy steps:
Created a particular segment in Imprice.
The segment included about 80% of the store's SKUs: all "foreground" and "background" items. Before, for some of these goods, the company had used rule-based competitive pricing; when self-isolation had begun, consumers had stopped buying a lot of goods from the segment.

Set "Maximum gross profit" as the optimization goal.

Set intervals of acceptable price changing for segment goods: upper and lower price limits for optimization algorithms.

From June 1, 2020, artificial intelligence began to calculate prices for 80% of the assortment.
Prices optimization details
Evgeny Bernitsky
CEO at
At this point, artificial intelligence had started to manage prices of about 2,000 SKUs. We monitored every step of optimization algorithms and tried to understand the reason for every price changing made by AI.

We got fantastic insights: Imprice recognized short-term surges in demand and immediately increased prices for the corresponding items, such as Vitamin D3, Melatonin, Zinc. Only later we learned that articles had appeared in the media stating these vitamins and supplements improve resistance to COVID-19. People rushed to buy the recommended, and sales of these items began to rise. Artificial intelligence detected the increased demand and raised the price of necessary SKUs. For example, we sold vitamin D3 at the highest price on the market: it started to be out of stock in other stores, and our sales grew at a price 1.5 times higher than usual. In July, the over-demand ended, and the algorithm lowered the price again.

As a result, the category of vitamins hit the second place in gross profit, while before it wasn't even in the top ten.

Another surprise was consumers were willing to pay more than we assumpted for many items from our "long tail" segment. Imprice identified these goods and increased prices. Sales in pieces remained about the same level as before, but now we earned more on each item sold.

Finally, there were many goods which prices automatically followed competitors' ones before, and consumers stopped buying those from the start of lockdown.
Artificial intelligence reduced these items' prices below the market level, and surprisingly demand reignited.
What exactly happened? Suppliers' prices went up, all stores raised shelf prices, but people had no willingness to pay so much, with a new lower living standard. All competitors made the same pricing mistake, and we just followed the market and lost our sales. Imprice switched our prices back to the pre-COVID-19 level, so sales returned immediately, with a still good gross profit.
In July, the company assessed the results of price optimization. They compared June sales with sales data in May 2020.
They saw a slight decrease in margins, but other business metrics improved, and gross margin increased by 20.1%.

The entire online store
+20.9% Revenue growth

+20.1% Gross margin growth

-0.7% Margins level fall

+8.0% Average Order Value growth

+3.7% Items per order growth

+11.9% Number of online orders growth

+31.9% Sales in pieces growth

+13.1% Number of unique SKUs sold growth

+23.0% Revenue growth

+12.6% Gross margin growth

-8.5% Margins level fall

+4.8% Average Order Value growth

+5.8% Items per order growth

+17.4% Number of online orders growth

+48.6% Sales in pieces growth

+15.0% Number of unique SKUs sold growth
Assortment with AI-driven price optimization (80% of total SKUs)
+19.6% Revenue growth

+42.5% Gross margin growth

+19.2% Margins level fall

+14.5% Average Order Value growth

+4.4% Items per order growth

+4.4% Number of online orders growth

+18.2% Sales in pieces growth

+12.7% Number of unique SKUs sold growth
The company's metrics improved against the ongoing crisis in the sports nutrition market:
In June 2020, Gyms in Moscow and St. Petersburg were still closed.
Internet traffic in June even decreased compared to May 2020.
Competitors can make wrong decisions.
Demand sensing helps to exceed business goals today
Evgeny Bernitsky
CEO at
What have we learned after launching price optimization?

First output:
Even top competitors are not gods and can make mistakes. Now is a time of turbulence, and the business environment changes rapidly every day. In our case, all stores made sports nutrition too expensive for consumers, which led to sales falling.

When sales dropped down, it better not to repeat: "This is a crisis; people stopped buying." Test different prices, try to put them below the market level if margins allow. We made this step, and our disappeared demand reignited.

Second output:
The company's experts are not gods either. Our specialists assumed as main competitors large stores, but in fact, low-priced stores with a bad reputation "stole" sales and consumers from us. We switched from assumptions to real data and improved KVIs' sales.

Third output:
It's possible to find underpriced goods in the assortment, even during an economic crisis. We increased such items' prices and improved gross margin, selling the same number of pieces.

Before, we lost profits because we missed short-time shortages of goods at competitors' stores. There are only relatively small chains and stores in our market, not large chains with perfect supply management. Stores have a short-time lack of some supplements and vitamins often. With Imprice, if some popular items disappear from competitors' stocks, the AI-module immediately detects a surge in conversions, rapidly raises our prices of such goods, and our company gains more profits.

Another example is "background", "long tail" goods. Since July, the demand for sports nutrition has revived: gyms have opened, and sportspeople have started to buy protein. Protein for strength training is an expensive product, and its price reaches 50-60 euro. Consumers buy something less costly with protein often, for example, dietary supplements. Imprice records which products are often purchased with protein and raises prices for these complementary goods; so improves profits per order.
Talk to Imprice pricing experts: