NVIDIA POWERS LATEST ADVANCES IN FINANCE TECHNOLOGIES
GTC brings together some of Europe's top financial institutions to showcase how GPU and deep learning technology are being applied in the Financial Services sector. Sessions will feature a number of user cases including how deep learning solutions can dramatically improve productivity in eCommunications surveillance and enable efficient discovery for GDPR compliance. The Finance track will also highlight current innovation in the traditional Quant analytics application segment.
HEAR FROM INDUSTRY LEADERS IN FINANCE
This track focuses on state-of-the-art research in analytics, speech recognition and fraud detection plus much more. Hear from industry experts, connect directly with NVIDIA engineers, and get valuable, hands-on training from the NVIDIA Deep Learning Institute (DLI). Get the knowledge and experience you need to get the power of deep learning working for you.
NVIDIA Deep Learning Institute
The NVIDIA Deep Learning Institute (DLI) offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning.
Join us for the following Finance themed labs on Wednesday, 11th October:
Trading Strategy for Finance using LSTMs
13:00–15:00 h
Level: intermediate
This Lab demonstrates how to structure and train LSTM deep neural networks to predict time series behavior using technical and fundamental inputs. This lab is based on the dataset in the Kaggle contest called the ""Two Sigma Financial Modeling Challenge"", and contains anonymized features pertaining to a time-varying value for financial instruments. We use the LSTM network to train a predictor of the target variable optimized to find the highest possible correlation with the labelled targets. The lab uses the TensorFlow deep learning framework and Python data science tools like Pandas to perform data cleaning, RNN network construction, training, and evaluation.
After taking this lab you will be able to:
-
Structure and train an LSTM network in TensorFlow to accept vector inputs and predict a target
-
Prepare time series data and test network performance using training and test datasets
-
Understand the steps in creating an end-to-end RNN time series prediction algorithm in TensorFlow that could be benchmarked against traditional machine learning techniques
Prerequisites:
-
Working knowledge of basic scientific python
-
Basic level knowledge of TensorFlow
Algorithmic Trading using Deep Autoencoder based Statistical Arbitrage
15:30–17:30 h
Level: intermediate
Note: This lab is taught at GTC Munich as an exclusive beta test offering
Linear techniques such as PCA are the workhorse of creating eigenportfolios that can be used for statistical arbitrage strategies. This lab demonstrates using a deep autoencoder to learn a hierarchical, non-linear basis set that can be used to reconstruct security return data. Anomalous deviations (spreads) in reconstruction error are used as (mean reverting) signals for creating long/short positions. P&L of the strategy can be calculated and benchmarked against traditional linear techniques. This course uses TensorFlow and Python for the code examples covered during the lab session.
After taking this lab you will be able to:
-
Structure and train a deep autoencoder in TensorFlow and Python.
-
Use the autoencoder as an anomaly detector to create an arbitrage strategy and perform hyperparameter optimization over the autoencoder.
-
Calculate P&L of the strategy
Prerequisites:
-
Working knowledge of basic scientific python
-
Basic level knowledge of TensorFlow
-
Knowledge of PCA techniques for statistical arbitrage