Decision Science in Action

I joined   CoreCompete   on  Feb 18, 2013 Monday. It has been a great learning and exciting experience. When I walked into Banjara Hills, Hyderabad office of Core Compete (now shifted to Gachibowli, 3rd office) only thought in my mind was did I take wise decision by choosing Core Compete over a global giant.  Today, I can say that it was the best professional decision I have taken. I feel proud and amazed when I think about our growth from 4 to 200+ in period of 6 years in the niche business of advance analytics and big data technology and recognized as fastest growing consulting organisation in North America ( http://www.consultingmag.com/fastest-growing-firms-2016/   ) for last three consecutive years. Yes, we are growing fast, but that’s not the only reason that I love working at Core Compete.  In last 6 years I worked for multiple clients across multiple domain using different advance analytical techniques and technology platform.I got opportunity to work in different doma

Product propensity models are developed to identify   the  customers or observations those  have high likelihood of responding to any cross-sell campaign or any event of interest.  Model d evelopment which includes has multiple steps requires extensive efforts. 1. Identification of business objective or business problem. 2. Identifying analytical objective  3. Identifying data scope and time window.  4. Data preparation and exploration 5. Data treatment and variable reduction 6. Model training and validation 7. Model selection and interpretation  8. Business approval  Steps to automate the model scoring for its periodical usage. 9. Model deployment  10. Periodical Model Scoring  Once the models are scored and used in the campaign for targeting customers to cross sell the product of interest, effectiveness of model must be measured. I am going to discuss the different ways to evaluate the model's robustness. This should not be

Data science is one of the  most promising field for bright future.  Various Gartner reports state that most of the organisations are going to invest more strategically to use the power of analytics to drive their business decisions.  Top banks and retailers have been using the data analytics for acquiring new customers, promotional initiatives, product pricing  etc  by setting up centre of excellence in analytics in India. In last 5 years analytics profession has caught lot of attractions in the job market.  Number of institutions in India and outside India have launched academic programs including online and on campus certificate programs. Question is which program is best? I do not know but I can definitely argue that M Tech in IME at IIT Kanpur is an excellent launchpad for career in data science or analytics.There is also another M Tech program at IITB which is among top programs for data science. These are two top programs which are producing talent pool for analytics for ye

Big Bazaar, biggest hypermarket chain in India and has grown into tier - 2 cities besides being leading chain in metros. In the competitive retail world Big Bazaar keeps trying to innovate itself and comes up with always new type of offers for their customers many of which are successful and many are debunked by the customers.  Big Bazaar is recently promoting an offer in their stores. This states 2000 INR Monthly cash/bonus vouchers with minimum purchase of INR 2500. Obviously this looks very attractive to the customers who visit the stores but is it really attractive or just a trap. Big Bazaar will definitely see higher footfalls and high spend due to this so called attractive offer. But is it good for Big Bazaar in long term...? Booklet front page Lets dig deeper and try to find out whether the offer is attractive for the customers. The pair of words cash/bonus voucher is completely misleading. Customers think they will get voucher worth 2000 INR which they can redeem dur

When I search for the mentioned error I get the link solution provided administration oriented but developers do not have access.     http://support.sas.com/kb/52/716.html Please see my solution below proc options option=config; run; proc options group=languagecontrol; run; /* Show the encoding value for the problematic data set */ %let dsn=item_information_may16; %let dsid=%sysfunc(open(&dsn,i)); %put &dsn ENCODING is: %sysfunc(attrc(&dsid,encoding)); /*Renaming item desc file  (encoding=any) allowed reading****************************/ data tmp.item_info_curr; set hc.item_information_may16 (encoding=any); run; /*gave error*/ data item_info_curr; set item_information_may16; run;

This was my first global conference of this kind. I have attended academic conferences but those were not in this scale.  I feel proud to be a part of such a large community. SAS has opened itself to open source technologies by adopting new architecture called SAS Viya.  My takeaways from the conference are 1.        Open and Cloud ready SAS Viya architecture is designed for varied skillsets to solve all types of business problems. Initial offerings come with point and click interface and programming features. This means I need to add more skillsets quicker than others to keep myself valuable. For more details, click http://www.sas.com/en_us/news/press-releases/2016/april/sas-viya-sgf16.html   and http://www.sas.com/en_us/software/viya.html . Personally, I am excited about this as I think new architecture opens the door for more innovation. There are lot to learn about this to be able to use it efficiently. 2.        Data visualization is in high demand. SAS had booths fo