Data Mining 101: Why Dealerships Need to Go Beyond Traditional Equity Mining - Data Mining 101: Uses of Data Mining in the Auto Industry

by John Kehm

For over two decades, brands have turned to data mining techniques to fuel critical business decisions.

As computer storage capacity increased throughout the 1980s, companies found themselves with too much data to be analyzed by traditional approaches. By the late 90s, the process of data mining (using tools like AI to detect patterns and relationships in large datasets) was born.

Today, data mining powers many conveniences and capabilities we often take for granted, ranging from email spam filters and credit card fraud alerts to personalized suggestions from Amazon or Netflix.

Just as the process was born to enable brands to evolve beyond traditional data analytics, data mining empowers auto dealers to move past antiquated techniques like equity mining to make way for more actionable and comprehensive insights – and more impactful results.

In this blog post, we take a step back and look at this important technology, answering the questions:

How does data mining work?
What’s the difference between equity mining and data mining?
What are the key uses of data mining in the automotive industry?

Data Mining 101

How does data mining work? To start answering this question, we can return to the days of Sesame Street.

In the classic educational song “One of These Things,” children are shown a video of four balloons and told, “One of these things is not like the others. One of these things doesn’t belong.” They’re asked to identify which balloon isn’t like the others by the end of the song, at which point the red balloons float away and only the blue balloon is left.

A child can quickly identify the blue balloon as not belonging since its color stands out more than anything else. However, in the eyes of data mining, the color of that balloon is just another data point used to draw a conclusion.

Instead of analyzing each individual attribute, data mining works by considering numerous factors and conditional logic to find patterns and quickly draw conclusions from massive data sets. Now, imagine that instead of four balloons and two colors, there was a warehouse full of balloons of various colors and shapes. While a human could spend months trying to catalog each balloon by various attributes to try to identify the one that “didn’t belong,” a data mining tool accomplishes the task in mere moments.

The Difference Between Data Mining and Equity Mining

The ability to analyze a variety of factors and how they correlate vs. any one factor on its own is the key difference between equity mining and data mining tools.

Just as a child may solely consider the color of the balloons in the previous example, equity mining tools look at a singular reason a consumer may be a good candidate for a new vehicle without considering the variety of other factors that could influence that decision. With negative equity surging to an all-time high in 2020, this approach has lost much of its original value when it comes to automotive lead generation.

On the other hand, modern data mining solutions analyze a broad range of factors from various sources, including a dealer’s CRM, DMS and demographic data to determine who might soon be on the market for a new vehicle.

For example, imagine analyzing the profile of a customer who has six months left on her lease. That factor alone likely isn’t setting off any alarms, but when you also consider that individual just started a new job and recently moved to the suburbs, she becomes a prime prospecting opportunity.

How Data Mining Works in the Auto Industry

New applications of data mining continue helping the automotive industry evolve to meet new challenges – from dealers all the way up to OEMs.

For example, during Toyota’s rapid North American sales growth in the late 1990s and early 2000s, the company turned to data mining to reengineer its logistics operations, allowing it to increase shipment volumes by 37% and cut time to vehicle delivery from 37 days to 18, with just a 3% staff increase.

At a dealership level, we’ve already discussed how data mining powers more comprehensive and intelligent lead generation efforts, but that’s only one example of its ability to drive dealership efficiency and profitability.

At Mastermind, data mining powers many of our highly successful tools and services. Fueled by data from a dealer’s own DMS and CRM data, as well as IHS Markit, TransUnion and CARFAX, Market EyeQ’s proprietary algorithms generate insights that support real-world business results.

Critically, in this challenging sales environment this combination of data mining and high-quality data enables dealers to move past solely relying on equity mining tactics to engage with a broader pool of high-quality sales leads and empowers dealers to engage prospects more effectively.

After analyzing thousands of data points, Market EyeQ creates marketing and talk tracks personalized to each prospect’s individual needs and factors in considerations such as buying history, financial considerations, available dealership inventory and more. These personalized marketing campaigns are designed to quickly move prospects through the buying journey, targeting buyers via channels and at the times predicted to be the most impactful for them.

The results speak for themselves: Dealers who market with Market EyeQ produce 15x ROI and the lowest cost-per-sale in the industry.

Interested in learning more about how comprehensive equity mining could empower your dealership to improve its sales process? Contact us for a free demonstration.