Survey Data Analytics – Generating Profitable Insights

Published on April 10, 2018 by Santosh Kumar

The top 25 market research companies are increasing their focus on and investments in social media, data visualization, and analytics. The research industry’s drift toward analytics is well under way.

More than 70% of respondents (comprising suppliers and clients) in the GRIT survey conducted by GreenBook in Q1 2018 showed interest in analytics, as per the GRIT Q3-Q4 2017 Report. Around 30% used analytics in their research, while approximately 30% were considering the use of analytics.

Do analytics apply to only Big Data (and not survey data)? Usually, when we hear the term analytics, the first thing that comes to our mind is Big Data. Analytics is associated with mostly prediction and prescription. It can be categorized into four main branches – descriptive, diagnostic, predictive, and prescriptive. The right analytics technique, selected on the basis of the research objective and type of data collected would yield insights into even survey data.

We can safely apply descriptive and diagnostic analytics to survey data, to derive insights and support results and trends that emerge from tables and charts.

Analytics techniques used in survey data include:

• Key driver analysis

• Perceptual maps

• Stated vs. derived importance analysis

• Maximum differential analysis

• Discriminant analysis

• Net promoter score, net satisfaction score

• Brand value rating and product power rating

Below is a real life example of how our clients are using analytics to drive business transformation.

A leading cruise company was facing a challenge in identifying key attributes which would improve the willingness of customers to recommend their cruises. Although the company had the necessary data it needed it to be processed and presented in a way which enabled management to take data driven decisions.

We worked with the client and used our expertise in R to cleanse data and perform complex computations on the survey data to convert it into actionable insights. Further, we integrated our survey tool with R to fetch the survey data in real time. Finally, we integrated R script with a visualization tool to showcase the results over a web link.

Using the solution, the client could easily deep dive the results based on destination, ship, and sailing frequency (daily, weekly, monthly, and quarterly). Consequently, using the insights the client increased the ‘willingness to recommend’ KPI by 14%.

---

---