**Registration is mandatory** (Link to register is provided below)
Due to a high amount of positive responses on our Hidden Markov Models webinar last week and due to a high amount of requests from the attendees of the same to do an extended version of the webinar, Byte Academy brings you a webinar series where we'll deep dive into Stock price prediction using probabilistic graphical models hosted by Usha Rengaraju.
This session will be broken down into three parts and will be presented to you in the form of three, hour long webinars on the dates 20th December and 24th of January. It includes hands-on in solving one of the most common problem in quantitative finance -- Stock price prediction
using probabilistic graphical models. The programming language used in the workshop is Python.
December 20th 2018 (8 PM - 9 PM)
Part 1 : Introduction to Probabilistic Graphical Models
This part includes history of probabilistic graphical models from its origin, Bayes theorem, types of graphical models--Directed
Graphical models and Undirected Graphical models , basic concepts involved in both types of models and case studies for both types
models. It also includes why one should choose to use Graphical models.
January 27th 2018 (8 PM - 10 PM)
Part 2 : Introduction to Directed Graphical Models (Bayesian Networks)
This part includes the basic concepts involved in Directed Graphical Models like conditional Independence, d-separation and also introduces
the concepts involved in one type of Directed Graphical Models -- Hidden Markov Models .
Part 3 : Hidden Markov Models and case study of Stock Price Prediction
HMMs are capable of predicting and analyzing time based phenomena because of which they are widely used in fields like Speech recognition ,
natural language processing and Financial Market Prediction.Stock market prediction has been one of the more active research areas in the
past and various machine learning algorithms have been applied with varying degrees of success. Stock Price forecasting is still severely
limited due to its non-stationary, seasonal, and unpredictable nature. HMMs are capable of modeling hidden state transitions from the
sequential observed data. The problem of stock prediction can also be thought as following the same pattern.The price of the stock
depends upon a multitude of factors which generally remain invisible to the investor (hidden variables). The transition between the
underlying factors change based on company policy and decisions, its financial conditions, and management decisions, and these affect the
price of the stock (observed data). So HMMs are a natural fit to the problem of price prediction.
About the Speaker: Usha Rengaraju is a polymath and unicorn data scientist with strong foundations in Economics, Finance, Business Foundations, Business Analytics and Psychology. She specializes in Machine Learning, Probabilistic Graphical Models and Deep Learning. Having completed Financial Engineering and Risk Management program from Columbia University with top honors, micromasters in Marketing Analytics from UC Berkeley and statistical analysis in Life Sciences specialization from Harvard, she has around 5 years of technical experience working in various companies like NeoEyed, Infosys, Temenos and Mysuru Consulting group.
Byte Academy (“Byte”) is a leader in industry oriented technology education with courses in Python software development, FinTech, Data Science and Blockchain.
Learn more about Byte Academy at http://byteacademy.co/
This is a paid event, please follow this link in order to register yourself and make the payment: https://imjo.in/Uryvn4