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 discuss PingAn's smart car insurance claims solution, which includes automatic vehicle picture estimation and anti-fraud detection. Learn how we reduced processing time for claims from days to seconds, increased operating efficiency, and cut billions in operation costs. Using the NVIDIA RAPIDS machine learning acceleration platform, we trained anti-fraud and risk-estimation models on GPUs, reducing model training time from weeks to hours. We will also share insights from our current work using GPU-Accelerated graph analytics to identify suspicious transactions, discuss mistakes we made, and offer suggestions for other data scientists based on our experience.

We'll discuss PingAn's smart car insurance claims solution, which includes automatic vehicle picture estimation and anti-fraud detection. Learn how we reduced processing time for claims from days to seconds, increased operating efficiency, and cut billions in operation costs. Using the NVIDIA RAPIDS machine learning acceleration platform, we trained anti-fraud and risk-estimation models on GPUs, reducing model training time from weeks to hours. We will also share insights from our current work using GPU-Accelerated graph analytics to identify suspicious transactions, discuss mistakes we made, and offer suggestions for other data scientists based on our experience.

  Back
 
Topics:
Finance - Deep Learning, Accelerated Data Science, Finance - Accelerated Analytics
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9863
Streaming:
Download:
Share:
 
Abstract:
我们将会讨论如何利用 GPU 加速金融领域的大数据图计算的方法和案例,并且分享通过 GPU 提升机器学习与数据分析效率和性能的经验。包括使用 NVIDIA Rapids 机器学习计算平台,在 GPU 上实现快速的机器学习建模和图数据分析计算,从而缩短数十倍的异常与风险检测分析的时间。本次演讲还会介绍利用 cuSparse 进行稀疏神经网络训练推理加速的实际案例,大幅提升金融领域的数据分析的效率,并根据我们的经验为其他数据科学家提供建议。
我们将会讨论如何利用 GPU 加速金融领域的大数据图计算的方法和案例,并且分享通过 GPU 提升机器学习与数据分析效率和性能的经验。包括使用 NVIDIA Rapids 机器学习计算平台,在 GPU 上实现快速的机器学习建模和图数据分析计算,从而缩短数十倍的异常与风险检测分析的时间。本次演讲还会介绍利用 cuSparse 进行稀疏神经网络训练推理加速的实际案例,大幅提升金融领域的数据分析的效率,并根据我们的经验为其他数据科学家提供建议。  Back
 
Topics:
HPC and Supercomputing
Type:
Talk
Event:
GTC China
Year:
2019
Session ID:
CN9100
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