Hard Goods Manufacturer Predicts If the Price Is Right with The Ople Platform

Case Study

Global Manufacturer

$10+ Billion

Company Description
As a global manufacturer of hard goods, the company produces over 25 million metric tons of good per year for customers across various industries, including civil construction, automobile, industrial, and agricultural.

“In our industry, pricing can sometimes be difficult. Different types and sizes of companies have thresholds for what they are willing to pay. With Ople, we built a pricing model that helps us to predict the price that reflects the value the customer places on our products, giving us better insights for more accurate pipeline forecasting.”

Key Achievements

  • New predictive model drove insights into customer behaviors and preferences that helped develop pricing that matched the value to that customer
  • Better pricing decisions improved customer satisfaction by offering pricing that was likely to be accepted with fewer back-and-forth negotiations
  • With the new pricing model being used for proposals across industries, sales productivity and job satisfaction increased
  • The Ople Platform allowed the sales team to quickly deliver an accurate pricing model without the need for assistance from the data science team
  • The success of the pricing model project is helping to push the use of AI and machine learning into other groups without dedicated data science support

The Pricing Challenge

Consumers today are accustomed to seeing the absolute price of the products they purchase in-person or online. With just a little bit of research, you can price out a computer, a refrigerator, or a bag of dog food. But for many items, pricing is much more fluid. For example, most car dealers have a sticker price for their vehicles, but this is rarely what is paid by car buyers.


For many industries, pricing is negotiated based on a number of different factors. These could include volume, whether the company is buying for resale, or the current availability of the raw materials of a finished product. In addition, the size of the company purchasing, or an ongoing relationship, can influence a discount or a premium price.


One hard goods manufacturer priced its products on many of these factors. With the wide range of industries and the different sizes of the companies they work with, pricing was a very time-intensive activity for this manufacturer. And when the pricing strategy was wrong, two things would happen – there would be a great deal of back-and-forth negotiations, wasting time and resources, or the potential customer would not sign the deal and instead look for another supplier.


Being an analytics-driven company, this manufacturer decided to apply machine learning to the pricing challenge. They gathered all of the data on pricing efforts for the past few years, including the results (whether there was a purchase or a renegotiation), and information about all of the companies they had presented pricing to (industry, company size, revenues, past purchasing patterns) in an effort to find a pattern in the data. 


What they lacked were dedicated data science resources in the Sales department. When they took the challenge to the central data science team, they were told that it would be a few months before they could even start to work on a pricing model. Determined to improve their pricing strategy, the Sales team decided to work on the challenge themselves.


They signed up for a free trial of the Ople Platform to test if their customer satisfaction team can improve the accuracy of the sizing model. 

When Business Users Build Models

Based on a referral from the data science team, the Sales team signed up for a free trial of the Ople Platform to build their own pricing model. With a deep knowledge of their business and their data, the Sales team was confident they could use the built-in intelligence of Ople to deliver a pricing predictive model that would help produce more effective pricing proposals. 


With the Ople Platform, the team simply uploaded the data into the system, entered information about what they were trying to predict, and Ople did the rest. After analyzing the data and the challenge, Ople was able to help the Sales team build their first pricing model in a matter of hours. 


With the platform’s model explainability features, it was easy for the Sales team to understand how the model worked. And by changing different variables, Ople’s What-If Simulation features allowed the team to simulate how pricing should change according to various factors. In fact, the ease and intuitiveness of the Ople Platform encouraged the team to add more data to build more models to test if the additional data resulted in a more optimized model. 


The ease of use of the Ople Platform allowed a team of Sales leaders and data analysts to quickly deliver a highly-accurate predictive model tuned to their specific business case. With Ople, they were able to accomplish in just a few days what the data science team would not even have been able to address for a number of months.

The ease of use of the Ople Platform allowed a team of Sales leaders and data analysts to quickly deliver a highly-accurate predictive model tuned to their specific business case.


The Results

The Sales team has been extremely happy with the new pricing model. Using the model, they are able to predict what pricing will appeal to companies for each and every deal. Not only are they saving time and reducing frustration, but they are also increasing the satisfaction of customers during the critical negotiation process. 

Moving forward, the Sales team is looking to enhance the pricing predictions with additional information about their customers, different products and applications, and some outside industry data to see if they can improve the predictive accuracy of the model. Furthermore, they are thinking of developing an application that will allow the Sales team to start looking at pricing earlier in the sales process to help guide their dealings with prospects and customers. 

Based on the success of the Sales team, the company sees the value in arming their business users with automated machine learning (AutoML). As adoption of the Ople Platform reaches new groups, the company is poised to transform their business with AI.

The Ople.AI Platform

The easiest way to accelerate decision making and reduce risk with predictive analytics

With the Ople.AI Platform, you are only a few clicks away from building predictive models to derive optimal business recommendations with reduced risk.