Stay tuned – Receive JSM-news !

Join the JSM mailing list to receive our latest updates.
Email address
ABOUT
All too often companies have only the vaguest idea about what kind of data they’re holding; because such data is very often hidden deeply away in a variety of databases and fragmented across different departments. We identify this data and bring it to light, making it visible, cohesive, comparable and easy to understand so that it really does support YOU in making the right decisions. And if need be, we can also identify any lacking data and define a concept to fill in the gap.

Determining what drives a brand’s perception, using Jaccard Analysis

Posted by on Dec 6, 2017 in Case Studies | No Comments

Image Courtesy: www.reviewtrackers.com

OBJECTIVE

A client approached us intending to know the attributes which play a major role in buying a non-luxury car and the ones that are least impactful. The objective of the study was to identify the attributes (key drivers) that drive a non-luxury car brand’s sales or image, customer satisfaction, loyalty and retention, etc.

APPROACH

To begin with, we identified all the attitudinal variables, from the survey, which impact sales or the brand image. We applied Jaccard Analysis to the data to determine the importance of the attributes/variables the client was interested in. In this particular scenario, Jaccard came out as a better alternative, in comparison to Predictive Modelling, as it allowed us to focus on each attribute.

The Jaccard technique works by pairing each attribute with the dependent (target) variable and the strength of association in each pair is calculated (one-by-one). The stronger the association between an attribute rating and the target variable, the more important we assume the attribute is in driving brand sales/image, etc.

OUTCOME

The client had data-driven insights on the attributes/features that need to be prioritized.

Using the Jaccard Analysis, we were able to calculate the Jaccard Coefficient value for all the attributes (ranging from 0 to 1) and hence, identify the impact of all the attributes on the brand’s success, in the decreasing order of their impact.

SAMPLE OUTPUT:

Note: Here in the chart, Jaccard Coefficient values have been depicted as percentages.

If the Jaccard Coefficient value for an attribute is close to 1, it means that it is a key (+ve) differentiating attribute. However, if it is closer to ‘0’ for an attribute, it means that its impact on the brand’s success is lesser in comparison to other attributes. Jaccard Coefficients can also be seen as derived importance (drivers).

Mamatha

A post graduate in Statistics from Osmania University, I have worked on Data Processing and Analytics for over 10 years now. I am always passionate about learning new techniques in analytics and more.

More Posts

Leave a Reply