During the last 20 years we helped a number of companies to increase sales by turning their data into actionable insights.
We want to share several case studies:
With this experience we created Insightee.
An early-warning loyalty system that increases revenue
by helping your salesforce retain more B2B customers.
In a nutshell >>
B2B Automotive trading company, Czech Republic
The customer is a recognized B2B car trading company with EU-wide operations. Its rapidly growing business generates valuable data that are being transformed to an undisputable competitive advantage.
Salespeople at the company used to have limited knowledge of the B2B customers they work with. With few exceptions they mostly do remote sales calls. A rapidly changing environment causes also frequent changes in the account management positions. When they used to work with customers as per their best judgement, they achieved average revenue per sales call about €13.
1. Behavioural prioritization
We have connected to the purchase history data in the ERP system. Second, we created a connection to the call duration records in the PBX system. We had to clean up the phone numbers recorded in the ERP system. It was quite challenging because the formats varied, were often incomplete, and contained many different other data quality issues. On the other hand, PBX data was very well standardized. It was important to join the records from both systems via the phone number. In this way, we were able to detect moments when each customer was contacted by someone from the sales department.
There are four grades of customers. The best grade is to be contacted each week, while the fourth grade with the lowest priority is fine when contacted once a month. We have created a model that prioritizes the frequency of contacts with customers and also reflects the time since the last known contact.
The most important role played the Purchase Recency (i.e. the time since the last purchase order placed.) A slightly lower importance was given to the total annual Purchase Frequency. Third in the row was the annual Revenue. To someone that can sound surprising. But from experience we know that Recency and Frequency are significantly more indicative of future performance than Revenue. So that was the reason. We also mixed a drop of the Last Contact Recency and total number of calls with the contact in the “cocktail”.
Our model automatically prioritizes customers according to importance and with respect to graded goals.
In order for the result to be useful in practice, we had to take into account both working and non-working days of the week. Therefore, it was necessary to generate a corresponding recommended call plan for each salesperson. The scheduler was set up to find the optimal date, which is the working day of the week, for each individual customer in the system.
All this information was brought to the attention of individual salespeople in the form of daily reports and as an interactive dashboard. Key calculated customer information was also integrated into the ERP and CRM systems used.
With this guidance, salespeople became much more organized than before.
To add a motivating factor, we created a “leaderboard”. Individual salespeople (and management) could see how everyone is doing, who is a little ahead, who is slightly behind and what is possible with how many customers.
2. Predictive product recommendation
A predictive model analyzes past customer behaviour and suggests up to five cars that each customer is most likely to purchase.
The same purchasing history, as described above, was used to “train” predictive models indicating the relevant brands, makes, and other characteristics of cars to be offered.
We used an algorithm similar to that used in eCommerce to analyze the shopping cart.
We have ensured the visibility of recommendations for salespeople when calling individual customers.
3. Warehouse aging and optimization
Aspects of the aging of stored cars and the approaching time to production were mixed into the mentioned model for recommending vehicles for sale. A balance had to be struck between recommending what the customer was most likely to buy and what the aging warehouse had to “get rid of” first.
Salespeople started receiving our model-based recommendations on a daily basis.
They started to work based on scored customers and recommended times to contact them.
Despite high inaccuracy of the contact list and thus contacting only every second or third recommendation – since then the average revenue per sales call changed to approx. €21.60.
All relevant data processing and calculations take place during the night in a dedicated data warehouse. We use Microsoft SQL Server Standard Edition. This allows us to use its predictive modeling capability (for recommendation models). In addition to the aforementioned integration with ERP and CRM, we also use Power BI for interactive reporting and Microsoft SQL Server Reporting Services for sending daily “instructions” to individual salespeople.
When the effectiveness of the models was demonstrated in practice, not only were the UX aspects redesigned to allow even smoother use of the system, but the recommendation models were also integrated into the self-service online vehicle ordering portal.
Hierbas Organicas, Mexico
Hierbas Organicas (Organic Herbs) of Mexico is a company dedicated to distribution of the best tea, herb and spice products. Hierbas Organicas was founded in 2013 to bring better-quality products to customers and find teas, spices, herbs, superfoods, accessories and many more things to help customers live well, eat a healthy diet and give body what it needs. Hierbas Organicas has a variety of organic and standard products to suit all tastes.
Hierbas Organicas’s challenge was common to all small businesses. The company wanted a solution that would enable them to provide a more personal touch to their customers. At the same time, Hierbas Organicas wanted to nurture relationships with their first-time buyers. They needed an increased number of repeat buyers to achieve their desired growth targets.
1. Behavioral segmentation
It took no more than few moments to process the whole purchase history. The system automatically recognized various customer segments and the corresponding revenue potentials. By discovering two particularly large segments of lapsed customers requiring activation, Jose Alberto Apezteguia, Hierbas Organicas CEO, immediately knew whom to approach and how.
2. Predictive product recommendation
A predictive model analyzes past customer behavior and suggests up to three products that each customer is most likely to purchase. Thorough measurements indicate that these recommendations are roughly 85 % more likely to bring conversions compared to random product offerings.
3. Customer retention automation
After the initial validation, Jose Alberto decided to automate his weekly emails based on our behavioral segmentation and keep enhancing the communication using our predictive product recommendations. We determined the best days for the communication, which has made Hierbas Organicas digital marketing much smarter than before.
Once Jose Alberto saw the campaign’s results, he was blown away by the revenue it generated. The campaigns have exceeded expectations more than four times.
Furthermore, we also observed a 55% higher email Open Rate and a Click Rate 47% higher than those of previous campaigns. The company also registered an extraordinarily high number of orders from returning customers, which was the goal. That resulted in the highest customer loyalty the company had ever ever achieved after a campaign. Customer loyalty almost DOUBLED compared to the average impacts of previous campaigns.
Last but not least, the Average Order Value (AOV) resulting from our campaigns has been 75 % higher than the AOV of other efforts so far.
Craneballs Studios, Czech Republic
Craneballs is a game studio based in the Czech Republic. They create action games for smartphones and tablets, downloadable from app stores. The games often attract very high ratings. That’s why they’re famous in the player community.
Matej Rejnoch and his team had already heard about our successes before we met. During our initial conversation, we realized that their biggest challenges were player acquisition and in-game monetization. Since Craneballs is a startup, they need to grow. So increased revenue was a primary goal.
We were given all customer data from the game Overkill 2, and asked to show what we could do.
We ran our ‘behavioral segmentation’ model on all financial transactions from all Overkill 2 players. This helped us to discover a ‘VIP segment’ among the players. VIPs are players who have highest propensity to make repeated in-game purchases and to spend more money than an average paying player.
With that list in hand, Craneballs created a Facebook Custom Audience and prepared two acquisition campaigns. The first campaign was as well targeted and prepared, as they only could. The second campaign was exactly the same, but additionally targeted a Lookalike Audience derived from the Custom Audience prepared by us.
We let both campaigns run simultaneously for two weeks. Our campaign had more or less the same open, click and install rates and budget as the Craneballs campaign. But when we compared revenue in time from both campaigns, ours was clearly the winner.
Our way of running Facebook acquisition campaigns has proven to be very effective. We managed to increase revenue, profit and the average number of in-game purchases.
231% more revenue compared with the usual campaigns before.
Our campaigns shown increased ROI by 45.8% compared to the usual ones.
Number of in-game purchases increased by 63% thanks to our ability to find the ideal audience.
CGTrader is a virtual marketplace for buying and selling 3D models like the ones you create in AutoCAD or similar tools. By buying specific models, designers save time because they don’t have to create all the details of equipment in a bigger model. The marketplace also provides an opportunity for designers to monetize previously created models (a vase, an apple or maybe a pillow, etc.).
Dalia Lasaite, CGTrader’s marketing director, faced a tough challenge: How should she spend her marketing budget to achieve the largest possible company growth?
Email marketing was one of the most promising channels. They knew that incentives greatly improve sales, but they lacked the customer segmentation and personalization that would enable them to create the right incentives.
In the same way as Hierbas Organicas did, we processed the CGTrader’s data. That project was actually somewhat specific, because we made two “behavioral segmentations” for them – one for buyers, and another for sellers. CGTrader could customize its email messages and incentives for each segment. Some incentives struck us as very generous at first, but ultimately they returned increased revenue.
Compared to CGTrader’s previous email campaigns, we saw much higher Open & Click rates. These also led to a higher activity by both Buyers and Sellers, and thus higher revenue.
Below you can see the statistics of segmented email campaigns compared to the classic, “carpet-bomb” style of emailing.
One more takeaway from this was that the campaigns worked even with very basic email templates. It confirmed that people are primarily curious about content and real benefits, not about flashy design.
Bow & Drape, USA
Bow&Drape advertises itself as “the brand that inspires smart, stylish women to make a statement.” We met Chirag Nirmal, the Bow&Drape CEO, in Boston. He was aware of the power of data and the potential that personalization could bring to their company.
Bow&Drape were originally looking for a tool, model or approach that would increase the duration of customer visits to the company website. After looking at their Google Analytics, we agreed that a 25% improvement of the Average Visit Duration metric would be a success.
After analyzing their business and web, we proposed a website personalization model.
With that goal in mind, we pulled data from Google Analytics and trained a “predictive model” on them. It was then able to tell which products were more likely to be purchased during each visitor’s session. It was a matter of a few days to implement that model directly into the Bow&Drape website as a “You may also like” section.
We checked the impact of our changes. Not only was the initial goal achieved – people visiting the Bow&Drape website were so curious about the relevant offers that they spent almost 40% more time on the website. An even better “side-effect” was an 85% greater likelihood that the visitor would make a purchase after she clicked on a recommended product.