GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:

We'll talk about how we use deep learning and GPU-Accelerated portfolio construction techniques to generate a long-short portfolio. We start with a database containing more than 4,000 daily factors on more than 6,000 publicly traded U.S. equities over nearly 30 years. We'll explain how we apply deep learning to process this data and identify relationships that forecast relative equity performance at multiple time horizons. Our neural network identifies long-short portfolios that we combine into our final portfolio by using a CUDA implementation of a risk-parity algorithm.

We'll talk about how we use deep learning and GPU-Accelerated portfolio construction techniques to generate a long-short portfolio. We start with a database containing more than 4,000 daily factors on more than 6,000 publicly traded U.S. equities over nearly 30 years. We'll explain how we apply deep learning to process this data and identify relationships that forecast relative equity performance at multiple time horizons. Our neural network identifies long-short portfolios that we combine into our final portfolio by using a CUDA implementation of a risk-parity algorithm.

  Back
 
Topics:
Finance - Deep Learning
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9743
Streaming:
Download:
Share:
 
Abstract:
We'll discuss how natural language processing techniques can be used for predicting financial markets from news data. By adapting techniques from other natural language processing applications to news data and market signals, predictive models can be built. Due to the large volume of news data available, models must be trained, optimized, and tested using GPU acceleration.
We'll discuss how natural language processing techniques can be used for predicting financial markets from news data. By adapting techniques from other natural language processing applications to news data and market signals, predictive models can be built. Due to the large volume of news data available, models must be trained, optimized, and tested using GPU acceleration.  Back
 
Topics:
Finance, Artificial Intelligence and Deep Learning
Type:
Talk
Event:
GTC Silicon Valley
Year:
2017
Session ID:
S7696
Download:
Share:
 
 
Previous
  • Amazon Web Services
  • IBM
  • Cisco
  • Dell EMC
  • Hewlett Packard Enterprise
  • Inspur
  • Lenovo
  • SenseTime
  • Supermicro Computers
  • Synnex
  • Autodesk
  • HP
  • Linear Technology
  • MSI Computer Corp.
  • OPTIS
  • PNY
  • SK Hynix
  • vmware
  • Abaco Systems
  • Acceleware Ltd.
  • ASUSTeK COMPUTER INC
  • Cray Inc.
  • Exxact Corporation
  • Flanders - Belgium
  • Google Cloud
  • HTC VIVE
  • Liqid
  • MapD
  • Penguin Computing
  • SAP
  • Sugon
  • Twitter
Next