A “bottom-up” approach to data unification

How machine learning plus expert sourcing can unify customer data at scale.


Watch the free webcast Integrating Customer Data at Scale to learn how Toyota Motor Europe was able to unify its customer data at scale.

Enterprises that are capable of gaining a unified view of their customer data can achieve added business enhancements and user opportunities. Capturing customer data, however, can be a difficult task, as most systems rely on traditional “top-down” approaches to standardizing data. In a recent O’Reilly webcast, Integrating Customer Data at Scale, Tamr field engineer Alan Wagner hosts a Q&A session with Matt Stevens, the general manager at Toyota Motor Europe, to demonstrate how a leading enterprise uses a third-generation system like Tamr to simplify the process of unifying customer data.

In the webcast, Stevens explains how Toyota Motor Europe has gained a 360-degree view of their customers through the Tamr Data Unification Platform, which takes a machine learning and expert-sourcing “human guided workflow” approach to data unification. Wagner provides a demo of the Tamr platform, applied within a Salesforce application, to demonstrate the ability to capture and unify customer data.

In particular, this webcast explores how to:

  • Combine machine learning with expert-sourcing to ensure a high-level of scalability and accuracy
  • Bring together disparate data sources within one system
  • Quickly integrate new data, with existing data sets
  • Utilize open APIs to integrate with a variety of existing systems

Using machines and people to unify data

Stevens notes in the webcast that Toyota Motor Europe’s customer data is organized at a retailer level. This manner of organization has resulted in a massive amount of segmented customer data being generated in various countries. As the auto industry has become digitized, Toyota’s segmented data couldn’t keep pace with advancing industry standards. Rather than applying a traditional top-down approach of standardizing data, Toyota chose to deploy Tamr to catalog, connect, and consume all of their customer data.

Tamr takes a “bottom-up” approach to data unification — using automated machine learning algorithms to provide the scalability required to ingest large data sets. To ensure accuracy, Tamr asks data experts (professionals who serve as the current owners of the data) to provide additional context about the information being processed.

Bringing together disparate data sources

Toyota Motor Europe’s challenge was bringing together disparate data sources at a European (national) level. Various countries had their own methods for integrating data, yet these approaches became problematic as the complexity and speed of data increased with the rise of new digitized processes. As an example, Toyota’s customers expect to receive relevant information when they use Toyota applications, visit retailer websites, and when they go to the dealerships. A seamless handover in the digital-to-physical customer process is crucial, yet the company was unable to provide this type of innovation because their data platforms were being managed separately in different countries.

By consolidating millions of data sources, the Tamr platform was able to ingest Toyota’s existing European customer data and integrate it within one system. This unified view allows Toyota to meet user needs and provide customer service during both digital and physical interactions.

Integrate new data — no restructuring needed

An important factor in integrating customer data at scale is being able to quickly match new data sets with existing information. In the webcast, Stevens explains: “Introducing new sources of data was becoming a real issue for us. We wanted to start to tackle data integration at the European level.” Tamr uses machine learning algorithms to analyze and detect similar patterns in new data sources, and then merges the new sets with existing data. This allowed Toyota to bridge the gap between new and existing data sources.

Easy implementation was something Toyota took seriously when choosing Tamr. Thanks to open API’s, the deployment process didn’t require restructuring of the systems that were already in place at Toyota. Stevens adds that because the Tamr platform understands the entropy of data, Toyota can continually gain value in the data unification process.

Watch a live demo

Gain a better understanding of the process and benefits of using machine learning to unify customer data at scale in the live demo featured in this free webcast:

This post is a collaboration between O’Reilly and Tamr. See our statement of editorial independence.

Cropped image on article and category pages via Patrick Hoesly on Flickr, used under a Creative Commons license.

tags: , , , , , ,