Combining Social Media Insights with Statistical Insights for Improved Analytics
by Avik Sarkar (@avik) on Monday, 25 June 2012
- Data Analytics
- Session type
- Technical level
Various facts are discussed about organizations and brands on Social media. How can the organizations incorporate the findings from Social Media to improve Analytics process like identifying customer churn or finding users to target in a new marketing campaign? This can help in real time proactive action by organizations to retain customers or improve customer satisfaction. This 360 degrees view would help organizations increase profitability and have happy customers.
This touches upon areas of Big Data Analytics, Data Analytics & Industry solutions
In this session we discuss few real customer use cases to first extract the insights from Social Media (comments in Facebook, Twitter, blogs) using text mining on Big Data platform. Then we discuss the probabilistic approach to combine the social media findings with the in-house customer records. The combination of social media insights along with the customer records are used for improved prediction. These predictions can then be used to target action in real time to customers.
Analytics Tools used for these scenarios are: IBM SPSS Modeler, IBM Big Insights, Cognos Consumer Insight, SPSS Decision Management, SPSS Data Collection
Avik currently holds the position of Senior Architect in Predictive Analytics and Data Mining at IBM working on developing algorithms for SPSS and Predictive Analytics based industry assets. Avik is also involved in collaborative academic research in Geographical Information Systems and Big Data Analytics. Avik has over 12 years of experience in the areas of Predictive Analytics, Data mining, text mining, statistical modeling and related areas across verticals like telecommunication, retail, manufacturing, hi-tech, environment, insurance, economic forecasting, etc.
Avik received his Bachelors in Statistics, Masters in Applied Statistics & Informatics from IIT Bombay and PhD in Computing & Data Mining from UK. Avik has authored several technical publications and technology patents.