Success Story – How 4KST Machine Learning Helped a Bank Increase Its Sales

How Machine Learning Helped a Bank Increase Sales

Every company that works with sales goals and forecasts needs tools capable of identifying the best business opportunities—ones that are measured not only by the size of the deal but also by the likelihood of closing it.

Machine learning, a branch of artificial intelligence, is a powerful technology for making these kinds of predictions, although few companies currently use it for this purpose.

The following case study is a good example of how a bank was able to significantly increase its sales after adopting 4KST Machine Learning to predict which business opportunities were most likely to result in a sale, thereby enabling it to manage its efforts and track its progress toward its goals.

The financial institution’s challenge was determining which deals to focus on. Its sales pipeline within the CRM (a tool that displays and tracks a potential customer’s entire buying journey), while indicating the stage of the sales process for a given purchase or deal, did not show which ones were most likely to close.

To address this challenge, 4KST developed two sales propensity models: one monthly and one quarterly. Each model assigns a score (that is, a number between 0 and 1,000) that measures the probability of a deal closing within the month (monthly model) or within the quarter (quarterly model).

“Based on these two scores, salespeople and sales managers will be able to focus on the deals most likely to close and determine their action strategies. If they have a monthly or quarterly target to meet, they’ll be able to know exactly what the probability of reaching it is and can focus on the opportunities that offer the best chance of meeting those targets. This way, sales managers don’t just rely on the salesperson’s ‘gut feeling’ to know where to focus; they now have a powerful ML tool at their disposal,” explains 4KST founder Riccardo Lanzuolo.

See real results:

Of all the sales proposals, the bank closed an average of about 20% per month. The predictive model developed by 4KST revealed that half of these sales were concentrated in deals that received scores above 800 points. Furthermore, deals with scores above 950 points had a 98% chance of closing.

As for the proposals that received a score between 650 and 700, that probability ranged from 65% to 70%.

Looking back at the previous month, the manager knew what score was needed to close the deal, so he knew how far or close he was to his goal.

As a result, guided by a machine learning model that had learned from the behavior of his sales and leads, the manager knew how to guide his team’s actions.

Click on the image to enlarge it

Click on the image to enlarge it

With such precise—and valuable—data, salespeople were able to make rational, statistics-based decisions, ruling out deals with low probabilities of success, optimizing their efforts and time, and delivering better results for the company.

As we have seen so far, Artificial Intelligence can be applied to statistical models to make increasingly accurate predictions in virtually any company in any industry.

The example above refers to sales forecasts, but it is possible to adapt the model for other purposes, such as calculating a customer’s credit score, the liquidity score of any vehicle, or the school dropout rate, among others.

Our predictive models stand out from most of those available on the market because they are customized. This means that our proprietary algorithm can be adapted to any market niche. 

Are you interested in our solutions for your business? Talk to a sales consultant and learn more about our products!