JPK Group Business Forecasting and Analytics Forum March 1-2 • San Francisco, CA Utilizing Predictive Analytics to Identify Business Drivers for Growth Predict trends, understand customers, improve business performance, drive strategic decision-making, and predict behavior March 2, 1:00pm View presentation online at: https://jpkgroupsummits.com/attendee1 Prashant Gupta – Cisco Prashant Gupta is a senior data scientist and have been working in Silicon valley for 16 years. He is well known for his abilities to find patterns in the toughest of data and generating revenue from data.
19
Embed
Utilizing Predictive Analytics to Identify Business ...jpkgroupsummits.com/wp-content/uploads/AB105_Gupta-Prashant.pdfPrashant Gupta – Cisco Prashant Gupta is a senior data scientist
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
JPK
Gro
upBusiness Forecasting and Analytics Forum
March 1-2 • San Francisco, CA
Utilizing Predictive Analytics toIdentify Business Drivers for Growth
Predict trends, understand customers, improve business
performance, drive strategic decision-making, and predict behavior
March 2, 1:00pm
View presentation online at:
https://jpkgroupsummits.com/attendee1
Prashant Gupta – Cisco
Prashant Gupta is a senior data scientist and have been working in Silicon valleyfor 16 years. He is well known for his abilities to find patterns in the toughest of
data and generating revenue from data.
Utilizing Predictive Analytics to Identify
Business Drivers for Growth
Prashant Gupta
Principal Data Scientist
1
Quick Intro
• Data Scientist having fun in Silicon Valley for last 17 years
• Worked on interesting projects - Apple, Cisco, HP, Informatica, OOCL
• Recently had paper published in ISM ( Institute of Supply Management )
• Created “profitable” and “successful” small businesses in bay area
Visual Correlation analysis of inter-dependencies in various supply chain elements. This correlation graph shows cause and effect relationships between elements with wide variations in their levels of interdependence.
Blue = Greater Positive Correlation
Red = Greater Negative Correlation
Let’s start with – Understanding business without Bias & Ego
1. Data sources
• Transactional data ( What they buy )
• Support experience data ( What products they have issues with )
• Demographic data ( General data about their lives )
2. Building dataset
• Feel and understand the data
• Maintain good excellent data quality
3. Building / Testing / Refining models.
• No single model is good enough
• Iteratively increasing model accuracy
Household Income (Income; rounded to the nearest $1,000.00)
Gender (IsFemale = 1 if the person is female, 0 otherwise)
Marital Status (IsMarried = 1 if married, 0 otherwise)
College Educated (HasCollege = 1 if has one or more years of college education, 0 otherwise)
Employed in a Profession (IsProfessional = 1 if employed in a profession, 0 otherwise)