Seminar/Xmas Dinner (London) - Matthew Dixon - Machine Learning in Trading

Full title: Machine Learning in Trading: Implementing Deep Neural Networks for Financial Market Prediction on the Intel Xeon Phi

We invite you to our 2015 Thalesians LDN Xmas seminar & dinner by Matthew Dixon on "Implementing Deep Neural Networks for Financial Market Prediction on the Intel Xeon Phi" followed by dinner at La Tasca in Canary Wharf

Presentation at 6.30pm, Dinner at 7.30pm

On Arrival - A Glass of Sangría Tradicional

To Start - Tabla Espanola (to share) - Traditional Spanish cured meats with mixed olives, Manchego cheese, bread and oil.

Tapas Selection

Christmas Albóndigas (Madrid) - Turkey & pork meatballs, in a rich, sherry and cranberry sauce.Pulpo Gratin Y Queso GF (Galicia) - A medley of potatoes and octopus baked in a creamy lobster sauce and gratinated with Manchego cheese.
Pollo Marbella GF (Malaga) - Chicken breast, cooked with chorizo in a white wine & cream sauce.
La Tasca House Green Salad GF V (Navarra)
Patatas Bravas con Alioli (España) - Fried potato, with spicy tomato sauce and roasted garlic mayonnaise.

Choose from:
Paella de Carne GF (Valencia) - With chicken breast and chorizo.
OR
Paella Verduras GF V (Valencia) - With seasonal vegetables.

To finish - Churros - Doughnut twists, served with fresh strawberries and marshmallows, plus a rich chocolate sauce

Abstract:

Deep neural networks (DNN) have demonstrated their power in areas such as vision (think Google image search) and speech recognition (think Siri). Some financial firms are beginning to apply these techniques to market data and other information important for trading and investing. But training DNNs (that is, setting them to work to develop models) is extremely compute intensive. In this talk, Matthew will describe a DNN model for predicting price movements from time series data, then explain techniques that enable this model to exploit the parallel computing capacity of the Intel Xeon Phi processor in conjunction with multi-core CPUs.

Biography

Matthew Dixon, Ph.D., FRM, Assistant Professor of Finance, Stuart School of Business, Illinois Tech.

Matthew is an Assistant Professor and specializes in financial modeling, machine learning and high performance computing. Matthew began his career as a quantitative developer at Lehman Brothers in London before pursuing academics and consulting for financial institutions in quantitative risk modeling. Matthew is a chartered financial risk manager and principal consultant for Quiota LLC, a consulting firm for buy side risk management and trading analytics. He holds a Ph.D. in Applied Mathematics from Imperial College (2007), a Master of Science in Parallel and Scientific Computation with distinction from the University of Reading (2002) and has held postdoctoral and visiting professor appointments at Stanford University and UC Davis respectively. He has published several academic papers at the intersection of financial modeling and high performance computing, chairs the workshop on high performance computational finance at SC and is co-founder of the Thalesians.