Ashwin Sridharan
P O R T F O L I O
Hi there! Welcome to my portfolio website.
My name is Ashwin and I am a graduate student pursuing Information Systems Management at Carnegie Mellon University’ Dec 20, based out of Pittsburgh, PA. Master’s in Information Systems Management (MISM) at CMU is ranked as the World’s Best Graduate Program with a comprehensive curriculum having a blend of Business, Technology, Data and Management courses. Please click on the picture below to learn more.
Biography
Being a business technologist, I thrive at the intersection of Tech & Business and love straddling both worlds.
I spent the Summer of 2020 working with the German software major SAP as a Product Analytics Intern, focussing on their procurement software solution SAP Ariba to generate actionable insights from troves of customer data, inspiring tangible business & customer outcomes.
Prior to my masters, I was a part of the Advisory arm of the Big 4 firm Ernst & Young (EY) in India, operating in the Financial Services industry. As a Consultant, I was constantly challenged with business problems of various shapes and sizes of the EY global clientele, which I unraveled through technology & data, building innovative digital products at scale.
I am deeply passionate about strategizing, developing and managing projects that fall on the focal point of Business, Data, Products and People. Below, I have highlighted a few of my personal projects.
Data & Analytics
Pittsburgh Crime Data Analysis
This project is all about analyzing crime data of Pittsburgh, Pennsylvania to discover interesting correlations and hidden patterns. The main objective is to obtain important insights enabling us to draw conclusions regarding the safety measures in the city and finally propound actionable recommendations based on race, gender, location and other crime specifics.
Predicting Video Games Sales using Machine Learning
The video game industry is a rapidly growing industry; in 2018, worldwide video games sales generated revenue of $134.9 billion. Since the recent COVID-19 pandemic has forced people to socially isolate and find activities to do alone, online gaming is seeing record numbers. Given this trend, companies are directing efforts in the development of new games. Game developers who want to capitalize on this growing market would benefit from knowing how best to spend their efforts in order to maximize sales. Thus, this analysis will be aimed at answering the following business questions:
- What are the factors and patterns in successful video games that result in high sales?
- How does the user and critic reviews impact the global sales?
- How does the sales vary between the Americas, Europe & Asia?
- What are some actionable insights which can be used by both sides of the aisle, creators and publishers, to enhance the user experience and increase the revenue?
In order to find answers to these important business questions, we use a supervised model (decision tree) & an unsupervised model (clustering) after conducting the preliminary data exploration & setting up the initial hypothesis.
Product Recommendation through Data Mining
Data Mining helps in the process of optimized targeting, making it easier for banks to adapt to a radically transformed business landscape in this digital era. Data builds relationships, helping banks and other businesses understand who their customers are and what their lives require. Based on a report, it was seen the banks that adopted data & analytics had an increase of about 10% in new customer opportunities over a year.
In this project, we use a unsupervised machine learning technique called Association Rule Mining or otherwise known as Market Basket Analysis, to help Banks and other Financial Services organizations understand their customers’ individual preferences based on historical usage patterns, and provide them with crucial insights on opportunities for product recommendations, cross-selling and up-selling.
Exploring Consumer Behaviour using Predictive Analytics
Predictive analytics is the use of advanced analytic techniques that leverage historical data to uncover real-time insights and to predict future events. This is a proactive approach, whereby retailers can use data from the past to predict expected sales growth, due to change in consumer behaviours and/or market trends. This can help retailers stay ahead of the curve, compete effectively and gain considerable market share.
We use a supervised machine learning technique (Classification- Decision Trees) to understand and explore consumer behavior to help the manager of a retail grocery chain predict the factors that influence the number of customers buying organic products from the retail store and set forth recommendations to increase the number of customers opting for organic products in the future.
Digital Transformation Strategy
Future of Tech in Higher-Ed: An Impact Study
Case Study Available On Request.
Agile Project Management
Scrum & Kanban: An Implementation Study
Case Study Available On Request.