Machine Learning For Retail

by | Oct 12, 2018 | Case Study | 0 comments

Increasing Profitability via Automated Pricebook Management

Maximizing business outcomes within Retail 

Incorrectly recorded distributor agreements, missed opportunities for volume and promotional discounts, and price mismatches within invoices all translate to lost profits. Advoqt uses Machine Learning to solve these problems for retailers.


• Pricing Analysis

• Promotional Discounting

• Pricing Conflict Reconciliation

Advoqt Technology Group drives Digital Transformation for mid-sized businesses. Seasoned consultants, proprietary Machine Learning and Robotic Process Automation technology, and a vetted ecosystem of niche partners allow us to deliver integrated solutions that give you a measurable competitive advantage.

Advoqt was engaged by a national retailer to streamline their pricebook management process. During the discovery phase, Advoqt identified accuracy checks that could be built into the communication process between vendors and the Client to ensure that all available discounts were known and that the Client was not being incorrectly invoiced by their suppliers (distributors). The Client wanted a human operator in the first release that would be able to reconcile conflicts between the supplier data and the Client data, recommending further action to be taken either on the Client side or against supplier errors. This operator was then replaced by a machine learning model after a few months of training the tool.

Advoqt built a web-based pricebook management platform that integrates with the Client’s existing supply chain, product catalog, and invoicing systems. The platform contains multiple pricebook catalogs including the Client’s and that of the various suppliers they work with. To allow supplier access to upload pricing and catalog data, an online portal was created including automated and manual upload options.

On a daily basis, the platform reconciliates between the claimed invoices by the suppliers and optimizes the stated pricing for volume sold. In case of a conflict, the system notified an operator who would resolve the conflict in favor of either the Client or the supplier. The system automatically alerts the operator in case of lost margin, which may be due to the Client not purchasing at the lowest price available or in case the product margins were below the target goals of the Client due to a problem with the negotiated price. The system allows for custom business logic to generate alerts if other Client’s business rules were not met. After deployment of the platform, the Client is able to maintain profit margin compliance and reduce the number of lost profit occurrences.

Due to a large volume of data that is processed by the pricebook platform, Advoqt chose to leverage the Amazon Redshift distributed database technology with the gradient-boosted tree optimization algorithms hosted inside Docker containers. The use of container technology allows for scalability and process execution within strict time-performance demands.

To learn more about how Advoqt can help you implement ML in your organization please visit our website at www.Advoqt.com or call (617) 600-8161.

Download Our Case Study

* indicates required

Explore Other Resources from Advoqt Technology Group

SOAR is not just for Mature Organizations

The blog created by Rapid7 concerns security orchestration and automation tools. The blog gives a definition of what these tools do. A SOAR implementation would begin with defining and understanding the security issues being faced by the organization and thinking...

read more

Best SIEM Systems on the Market

Our fifth article is from Buyer’s Guide and is an article by Karen Scarfone of Scarfone Cybersecurity. This article gets into specifics concerning the top security information and event management (SIEM) systems. The tools collect security log data from many sources,...

read more

How to Prepare Your Data for Machine Learning

Our fourth article is a blog by Rostam Dinyari, a strategic cloud engineer, and concerns how an organization needs to gather and prepare data for machine learning deployment. A list of guidelines is presented. The first phase in data collection is to define the types...

read more

Share This Article

Click below to share on social media