Analytics Contact
Advanced Analytics at Tungsten
Predictive Analytics
Predictive Analytics Solutions developed by Tungsten are the outcome of powerful matching algorithms that enable predictive models to utilize enterprise data in combination with very powerful technology stack. These predictive analytics solutions allow business to act on a single piece of information, without having to worry about data science equations and complex associations of data.
Fraud AnalyticsFraud Analytics
Solutions for predicting fraud at accuracy rates never before seen using traditional methods
Churn AnalyticsChurn Analytics
Know which set of customers are most likely to cancel membership or know employee attrition using churn predicting algorithms
Social Influencer AnalyticsSocial Influencer Analytics
Optimize social media marketing campaigns by identifying which of your customers or prospects are most socially influential
Shopper AnalyticsShopper Analytics
Optimize transactional profits by knowing who are your full price buyers vs discount shoppers and predict which customer or prospects will respond to which offers
Custom AnalyticsCustom Analytics
Answer any business question by applying predictive analytics solutions on your enterprise data
High Performance Analytics
With high performance analytics solutions we help you generate high impact insights to quickly and confidently seize new opportunities and make better choices ahead of the competition.
Data MiningData Mining
Analytical modeling provides insights to drive better decision making. We help you to streamline the data mining process to develop models quickly by understanding key entity relationships and finding the patterns & clusters that matter most to you.
Text MiningText Mining
More than 80% of the data is unstructured and within it lies underlying business insights. The key here lies in evaluate text like a human brain would excluding the inconsistency and ambiguity. We help you implement sophisticated linguistic rules and analytical modeling tools which enable you to uncover insights hidden in big text data. Tungsten's Machine learning and natural language processing skillsets and techniques automate many time-consuming manual activities and our high-performance capabilities let you evaluate even large collections quickly.
Statistics & EconometricsStatistics & Econometrics
We help you reap benefits in any business unit function. Be it analyzing customer data, crunching sales data, optimizing supply chain operations or trying to detect frauds of any kind. Apply powerful statistical analysis to all your data to get the most accurate answers.
Prescriptive AnalyticsPrescriptive Analytics
We help you combine descriptive, inquisitive and predictive analytics to provide answers to the "So what?" and the "Now what?" indicating what should a business do to retain key customers or how can businesses improve their supply chain to enhance service levels while reducing costs and so on.
Case Studies
Sentiment Analysis for Financial Advisors in Large Financial Services Firm
The Customer

A premier Tier 1 Investment bank offering a full spectrum of solutions to large corporate, government and institutional clients to their strategic advisory, financing and risk management needs.

Business Scenario

The Wealth Management business had a big joint venture and business was spending an enormous amount of time and money to understand their financial advisor opinions about the new platforms, products and services.Sentiment Analysis had to beused to determine sentiments, emotions and attitudes of the FA. The text used for analysis can range from big document (e.g. Platformreviews,support tickets) to small status message (e.g. collaborating platform status messages) to determine:

  • User behaviour
  • Product feedback
  • User intentions
Tungsten's Solution

Tungsten's sentiment engine extracts and analysed sentiments for a given product and feature set. Lexicon was created using:

  • Common or default sentiment words
  • Negation Words
  • Blind Negation Words
  • Split words

On this lexicon, series of pre-processing steps were performed namely Pos tagging, stemming, exaggerated word shortening, emoticon detections, hash tag processing.

And then Sentiment calculation was done using various text analytics algorithms to generate clustered sentiments across various operating modules of platforms and products.

Features and business benefits of the solution

  • Sentiment Analysis generated through the system helped business take significant pro-active measures in resolving issues helping reduce FA attrition to ensure success of the joint venture activity
  • FA collaboration and throughput was improved significantly leading to increased business and reduced operational costs over next couple years