November Meetup - Introduction to Machine Learning

We will be holding our first meetup this Saturday, come over and join our discussion on current trends and opportunities in the fields of Data Science. Agenda: 3:00-3:30pm Mingling 3:30-4:15pm Tech talks 4:15-6pm Working on Use Cases. The talk will be: Introduction to Machine Learning - How to become a Data Scientist - Oleksandr Khryplyvenko, IMMSP NASU Abstract: The basics of Machine Learning theory, laying down the common themes and concepts, making it easy to follow the logic and get comfortable with the topic. Bio Currently, Oleksands is a post-graduate student at the Institute of Mathematical Machines and Systems Problems of the Ukraine National Academy of Science (IMMSP NASU). Among his interests are reinforcement learning and imbalanced datasets problem. Formerly, a Machine Learning specialist at Ecoisme. Before that, Oleksandr had a track record working as a Linux backend developer. As a developer, he worked with various technologies, from C and assembler to Erlang and Python, from embedded to clusters. In 2008, he graduated from NTUU “KPI”, Faculty of informatics and computer science. He started his career as a developer in 2002, as a machine learing expert – in 2014. In 2016, Oleskandr decided to go in for mathematics, as he understood that modern machine learning has some fundamental issues, which cannot be solved with a brute force. We also want to discuss some real life use cases, who is interested stays longer.. Case #1 Telco Customer Churn Customer churn can take different forms, such as switching to a competitor's service, reducing the number of services used, or switching to a lower cost service. This customer churn model enables you to predict the customers that will churn. Case #2 Up-Sell & Cross-Sell Recommendation Product recommendation is the ruling trend, the ultimate strategy in the e-commerce world. Product recommendations are a great way to help your visitors discover products on your online store and deliver a personalized shopping experience to them. Up-selling is when the seller encourages the customer to spend more than they had originally intended. A cross-sell is when you recommend your customer buy a product that compliments their existing purchase, but is from a different category or vendor. Case #3 US special event equities (looking for edges surrounding earnings) Historically (studied by academics) stocks have exhibited price momentum after strong / weak earnings. The effect used to last for a few days, but supposedly now it only lasts the day of earnings. We want to replicate this Strategy: http://www.wsj.com/public/resources/documents/FearandGreedJPM0922.pdf to show daily percent returns of the model & point in time strategy execution frames (to see what stocks were traded on each day, at what price, and how many shares)