Automated Commodity Group Classification

How ONE LOGIC uses data science to analyze natural language and automate and speed up manual ordering processes

The customer, a widely diversified international company with many different commodity groups, primarily uses paper when it comes to its purchase orders (POs). The orders stated on the POs are not automatically mapped in the ERP system; instead, they have to be manually entered, which can be very time-consuming.

The company asked ONE LOGIC to develop a data product that would streamline and speed up its order process.

The computer-based analysis and algorithm-controlled processing of words and language is now part of everyday life (think Siri, Alexa, chatbots, etc.). However, the customer’s orders varied greatly in terms of their structure and accuracy. Some orders would be missing specific item numbers or would simply refer to previous orders (“same product as last time”). The question was which matching & text mining tools would provide the most reliable proposals and enable these complex processes to be performed – and automated – within the company.



One option was to develop a self-learning product matching engine that would necessarily have to be highly adaptive, flexible and geared toward self-improvement due to the complex requirements involved:

  • Combinations of information from different systems (product ID, material information, order history, etc.)
  • Use of customer-specific terminology
  • Identification of synonyms, acronyms, ambiguous terms, etc.
  • Ability to understand the relative significance of potentially important words in certain positions

The solution had to make the process more efficient and save time without adding to its complexity. This is why ONE LOGIC opted to take a different approach: rather than raw data, it used tables from the ERP system (with PO numbers, PO items, etc.) as its basis. These historical orders had already been integrated into the system and could be used as a training data set.
Each order contains open text fields, fields with predefined products and/or information and categories with special commodity group codes that have to be completed. If the entries are not able to be allocated to a ready-made category, the Data Product Platform ONE DATA breaks down the order text into single words, then uses statistical methods, mapping, collaborative filters, etc. to determine their possible meaning, and calculates the likelihood that they refer to a certain commodity group, category, item number, etc. In the next step, this information is sent back to the department that oversees incoming orders for a final (manual) check.


By bringing ONE DATA into play and breaking down orders into single words, it was possible to automate a time-consuming manual process and convert paper orders directly into entries in the system. The process is quicker, more efficient and more secure, especially as the customer can check the order again at the end without having to spend a great deal of time on it.


Download ‚Automated Commodity Group Classification‘ for free

In order to automate and speed up the ordering process for an international company, ONE LOGIC developed a data product. The customer’s orders were mostly in paper form and were not automatically mapped in the ERP system, instead, they had to be manually entered in the system, which can be very time-consuming.

  • Historical orders are integrated into the system and used as a training data set.
  • The Data Product Platform ONE DATA automates the time-consuming manual process and converts the paper orders directly into entries in the system.