Name: Practical tips for algorithmic trading
Start: 2016-05-03T18:00:00-07:00
End: 2016-05-03T21:00:00-07:00
Location: Nitro

Introduction to Algorithmic Trading (Martin Froehler)

Quantitative Trading is the methodical way of trading. It's a $300b industry, and Quantitative Hedge Funds are considered to be the elite of Hedge Funds. Today, with more and better data and software than ever, the application of machine learning methods on financial data becomes increasingly popular in the industry. In his talk Martin will introduce some basic concepts of quantitative trading including indicators, measures, common pitfalls, and best practices to avoid them.

Martin worked for many years in the quantitative hedge fund industry - first as a quant, later as the head of quant research team. In 2014 Martin founded Quantiacs - the first marketplace for user-generated trading algorithms. Quantiacs vision is to make algorithmic trading accessible. The company connects user-generted trading algorithms and connects them to capital, so that “free-lance quants” can earn money without investing their own money.

____

Demo: Interactive Strategy Development (Nobie Redmon)

Nobie is going to use the Quantiacs framework to demo the development of a trading algorithm. Nobie will go through this process using several different trading logics and their impact on the backtest.

Nobie is the COO of Quantiacs. He developed algorithmic trading strategies himself and developed the Quantiacs Python Toolbox for simplified backtesting.

____

Practical tips for algorithmic trading (Jenia Mozgunov)

Creating a winning trading algorithm is a multistep process. The steps are: (i) get familiar with the trading platform and its limitations (ii) set up optimization and cross validation routines (iii) come up with several strategies and backtest them using (ii). Every step has its own tricks of trade that may be counterintuitive for the beginner. Some economists even think that stock prices fundamentally cannot be predicted. To be confident in either point of view, one should take a machine learning approach to the problem. The problem of predicting stock prices can be compared to image recognition and other machine learning classics. Difference is that it's not enough to predict well, one should find out how to make money using a prediction.

Jenia is a PhD student at Caltech. He won our Q3 algorithmic trading competition. Jenia used machine learning tools to write his trading algorithm that now trades an initial $1M investment. Jenia's algorithm currently has a live Sharpe Ratio of 2.08.

--------------------

Tentative Schedule:

6:00pm - 6:30pm - Networking

6:30pm - 7:00pm - Martin (Intro To Algo Trading)

7:00pm - 7:30pm - Nobie (Interactive Strategy Development)

7:30pm - 8:30pm - Jenia (Practical Tips for Algo Trading)

8:30pm - 9:00pm - Networking

--------------------

Quantiacs at DataByTheBay:

Note that Quantiacs will present at the first Data By the Bay conference matrix,May 16-20: data.bythebay.io (http://data.bythebay.io/). Regular admission until April 30th, Late Bird from May 1st.

Important Note: For building security purposes. You will be prompted for your first and last name when registering for this event.

Tony Tran

Alexy Khrabrov

David Andrzejewski

Dirk

SF Bayarea Machine Learning

Technology

Machine Learning

Computer Vision

Data Mining

Data Analytics

Artificial Intelligence

Practical tips for algorithmic trading

Nitro

Share

SF Bayarea Machine Learning

Practical tips for algorithmic trading

SF Bayarea Machine Learning

Details

Members are also interested in