Hi, welcome to this course! I’m Ernie Chan, managing member at QTS Capital Management, LLC, a commodity pool operator. A short history of my career. After I graduated with a Ph.D. in physics, I joined IBM’s Human Language Technologies group. I developed natural language processing systems while working there which was ranked 7th in a global competition. Then I joined Morgan Stanley’s Artificial Intelligence and Data Mining group where I developed trading strategies to support other trading groups. Later on, I worked with Credit Suisse’s Horizon Trading group. After all this experience, you must have thought that I must be extremely successful in deploying the machine learning techniques to trading and would have been making millions. Actually, my colleagues and I managed to lose millions using these techniques! At that time I didn’t know why and was shocked as I worked in the best of the firms and with the best of the groups. But now I know the reasons. The goal of this course is to explore machine learning techniques that can work in trading. This course is launched exclusively on Quantra’s website in collaboration with Quantinsti. In this course, you will learn about artificial neural networks which represent an extremely powerful set of machine learning techniques that can solve complex real-world problems. They are capable of modelling nonlinear relationships between extremely raw inputs and outputs. These techniques were around for many years but in recent years with optimized open source libraries and faster hardware, very deep neural networks can be created with ease and speed. In this course, you will learn two of the most popular Python deep learning libraries namely Sklearn and Keras to develop and validate deep learning models. You will learn the skills in deep learnings techniques which can be used to create your own machine learning strategies or enhance your existing trading strategies. This course consists of six sections. Each of the section will provide you answers to some of the most important questions and issues in neural network models. In the first section, you will be introduced to the simple neural networks, how they learn and how you can use them in prediction problems. In the second section, you will be taught deep neural networks and their implementation in Keras. The third section is on Recurrent Neural Networks which are specifically useful with time series data such as financial markets data. The fourth section is on Long short-term memory technique, which overcomes shortfalls of RNNs and is considered the most useful deep learning technique in finance. In the fifth section, you will learn about Cross Validation and Hyperparameter tuning, which are common techniques that you can apply to optimize any quantitative trading strategy. In the sixth section, you will learn how to handle some of the challenges that you might face when using a machine learning model in trading. This is an advanced course which assumes you would have some machine learning and programming experience, to begin with. The advanced topics are covered in an interesting fashion. You will be taught with the aid of videos, reading materials, quizzes, and lots of interactive coding exercises in Python so that you get both theoretical understanding and practical know-how of the concepts covered. I hope you enjoy learning on Quantra! Good luck.
algorithmic trading and deep learning algorithm deep learning in data mining live trading lstm lstm network lstm networks Machine Learning Algorithms machine learning course neural network python neural networks Python python for trading python machine learning quantra data science quantra machine learning quantra python quantra trading reccurrent network Recurrent Neural Network the you