f SetuServ

We synthesize text conversations like nobody else does!

Sign up for a FREE demo
Contact Number
Thank you! We will get back to you soon.

Comparison of mobile banking apps – based on the Voice of Customer

In a new series, we will be comparing user feedback for apps in a variety of domains using our unique approach to Natural Language Processing that combines machine learning with human curation. In the first of the series, we compare two US banking apps.

Subjects – American Express vs. Chase Bank
Data Source – Apple’s iOS Store
Time Period
Salient Insights
Customers indicate a positive overall sentiment for both companies, but Chase experiences a higher positive sentiment than American Express. It should be noted, however, that Chase’s positive sentiment is trending downward. As expected, the trend of positive sentiment tracks the ratings for each company.
Banking Apps 1
The primary difference between Amex and Chase is navigability within the app, with Amex lagging behind Chase. Additionally, customers do not rate Amex as high as Chase on quick access to updated account details
The bottom left quadrant represents opportunities for either company. While neither Amex nor Chase is performing highly the rewards tracking dimension, an improvement on this dimension could indicate an opportunity of differentiation for a company.
For a full report please click here
If you want to learn more about how SetuServ deploys this optimized solution for its clients, please visit us at our website www.mineforinsghts.com

Posted in: App, App reviews

Leave a Comment (0) →

Building a competitive edge in a crowded app market

The App market is hyper-competitive – For example, there are 100+ apps on Google Play store that allow you to create custom photos by cutting the image from one image and pasting it to the other image.
Also, customers are highly engaged with these apps. 100k+ customers rated these competing apps, and their reviews are a gold mine for insights on what customers love, hate and request. Identifying and acting on these insights is crucial to building a competitive edge in such a crowded market.
For example, one of the app makers mined thousands of app reviews & identified a high priority feature that customers requested on a consistent basis – “Adding a zoom feature for more precise cut/paste operations”. When the app maker added the first feature to the app in late February, customers got what they wanted and the reviews requesting that feature no longer showed up as shown in the blue line below –
However, a new relevant feature request started showing up in the reviews in March – “Ability to hide/unhide the magnifying glass”, as shown in the purple line graph above. Customers said that the newly rolled-out zoom feature overwhelmed their photos. When the app maker acted on this request by May, those comments went away in subsequent months.
This is an example of how app makers can use the feedback from their customers to improve their apps, assess how well they are working and stay ahead of the competition. However, recognizing and prioritizing feature requests or bugs amongst thousands of reviews is not easy with a cursory reading of reviews. A more systematic and scalable review mining approach is required to capture the insights that are actionable.
Given the constant threat of churn & the crowded competition, it pays to pay close attention to what the customer tells you and to act on it.
If you want to learn more about how SetuServ deploys this optimized solution for its clients, please visit us at our website www.setuserv.com or click here for a demo on synthesizing reviews.

Posted in: App, App reviews, Review Synthesis, Survey Synthesis

Leave a Comment (0) →

Unrealistic Expectations from Text Analytics Tools

Our last blog described how organizations can improve their Net Promoter ScoreTM by analyzing verbatim responses. In fact, today organizations have a wealth of information in various text data sources such as customer complaints, reviews and social media conversations. Most customer centric organizations deploy text analytics tools to glean actionable insights. But, still if you ask any analyst that “How often were you stuck with text analytics tools, and had to massage the data manually?” the answer would most often be, “Almost always.” And the underlying reason for this is the complicated and contextual nature of text analytics itself.


KeyFor example, an airline that used a leading text analytics tool to mine customer complaints had “upgrade to business class” as a key theme. However, this theme is not specific enough to drive any Action. It is unclear whether the customers complained about “upgrades that were cancelled” or “inability to use miles for upgrades” or were simply saying that the “upgrades are expensive”. Each of these specific themes would demand different action and it is very difficult for a software to extract insights at this level of specificity.


KeyAlso, accuracy is often a concern with text analytics tools as they can’t adequately interpret the context and nuance of human language. For example, as Andrew Wilson rightly noted in this article , most of today’s text analytics tools would classify the following statement as a negative comment about the Scion: “With the supercharger included on my Scion, it is one bad machine,” not being able to recognize the colloquial use of the word “bad” to actually mean “good”.


While specificity is needed to make the themes actionable, accuracy is needed to act with confidence (especially when the action is at a micro level). At the current rate of Natural Language Processing (NLP) technology advancement, it will be decades before technology evolves to the level of human interpretation. As a result, leading technology companies like Google and IBM have increasingly relied on humans to train, evaluate, edit or correct an algorithm’s work, as explained in this article in the New York times.


Organizations need to understand where NLP works best and where it doesn’t so that human review can be used to complement NLP. Because human review becomes expensive and time consuming as the scale increases, it is very important to optimize the combination of NLP and human review so that it is scalable & cost effective.


If you want to learn more about how SetuServ deploys this optimized solution for it’s clients, please visit us at our website www.setuserv.com or click here for a case study on synthesizing reviews.

Posted in: Social Media Synthesis, Survey Synthesis

Leave a Comment (0) →

5 secrets your Net Promoter Score (NPS™) can’t unlock

NPS surveys have been so successful, that the abbreviation needs no expansion in customer centric companies. The score provides several benefits. Its simplicity makes it easy to track, to disseminate to various parts of the organization and to compare against benchmarks.
However, what is still in its infancy is ACTION based on NPS. Recently, Jeremy, an analyst at an online retailer was faced with the same problem. His stakeholders were asking the dreaded “So what”? question followed by the even more dreaded “Why”? question. Jeremy’s stakeholders are not alone and analysts often don’t have answers.
It may seem obvious that the answers lie in the treasure trove of textual verbatim responses within the survey. But most companies lack a systematic and thorough process to unleash the power of this information. A deliberate reading of these responses can provide several benefits. A few of them are :
DriversIdentify the drivers of the scores – By analyzing the verbatim comments, the company over a few quarters realized that “Deals available” and “Speed of delivery“ were disproportionately driving their Promoters

RouteTrack department-level performance– This has to be done carefully and only after data has been synthesized over periods of time. The company uses the score in conjunction with the text analysis as a metric for incentives for their departments

leaf graphicDecide priorities  – Companies can use this information to decide priorities. While cursory and superficial readings may identify the top 1 or 2 drivers the real value lies in identifying drivers that are easy to effect and that move the needle. The company realized that “limiting changes to their site”, though low on the totem poll of drivers, was an easy fix that satisfied a decent chunk of high rollers

leaf graphicClose the loop with customers – A customer who feels heard is more likely to be loyal than one who is not. And if their request or suggestion is on your product roadmap even better. While harder to implement at a B2C company, identifying the grouses of borderline Passives can provide insights into how to convert them to promoters

leaf graphicIdentify customers for follow up research –  While some priorities will be clear after synthesis of verbatim comments customers can be identified  for follow-up research as well as for tracking.
However, we must admit that reading through comments is a challenging task especially when volumes of verbatim exceed a few hundred sentences a quarter. In our next post we will discuss some of these challenges and pitfalls and how they could be overcome. If you want to learn more please visit us at our website www.setuserv.com or click here for another use case of NPS verbatim synthesis.

Posted in: Net Promoter Score, Survey Synthesis

Leave a Comment (0) →

Which Tweets work best?

Organizations are increasingly seeking to engage with customers on social media. A challenge for organizations is choosing the kinds of messages that drive the most engagement. We recently analyzed the social media presence of some ad agencies, with a special focus on Twitter and derived insights that shed light on the issue.
The findings show that the tweets containing links to pictures and tweets on events, promotions and awards generate the highest customer engagement, as measured by the retweet ratio. Tweets containing hashtags, non-picture URLs, scientific research also have a retweet ratio that is better than the average.

  This trend was consistently true for each twitter stream from each of the 7 agencies  

An interesting finding was that, InTouch’s picture URL’s had an exceptionally high retweet ratio, as seen in the graph above. This may be driven by the fact that the pictures contained photos of executives and movie/sport stars.
To obtain these results, we at SetuServ analyzed about 15,000 tweets, from various agencies. SetuServ deployed its unique Skierarchy approach to Natural Language Processing that combines machine learning with human curation. Our approach allows us to glean insights with accuracy and granularity not possible with other solutions. Finding the right balance between machine learning and human curation is essential in getting accurate insights from text data. At SetuServ we believe we’ve done just that.
For more information, check us out at www.setuserv.com or call us at 312-823-4300.

Posted in: Social Media Synthesis

Leave a Comment (0) →

Thank you!!

We will get back shortly
Talk to us
Contact Number