Online Program Home
My Program

Abstract Details

Activity Number: 76 - To Open Source, or Not
Type: Contributed
Date/Time: Sunday, July 28, 2019 : 4:00 PM to 5:50 PM
Sponsor: Section for Statistical Programmers and Analysts
Abstract #305348
Title: TensorFlow Versus H2O, Predicting the SP500
Author(s): Kenneth Davis*
Keywords: TensorFlow; H2O; Neural Network; LSTM; SP500; Python

Data science tools can help us both better understand underlying phenomenon and better identify future courses of action. However, selecting the right tool for the job requires a further challenge and an art. The present analysis compares the well known TensorFlow package, in Python, to the lesser utilized but more statistically friendly package H2O, in R, to predict the SP500 stock market index as a multi-parameter economic time series. Results, innovations, ease or difficulty of use, and future applications of each data science package are reported. Local machine and virtual machine instances in Amazon AWS AMIs are evaluated. Overall fit of economic parameters are examined. TensorFlow and H2O offer unique and powerful neural network and recurrent neural network/LSTM solution pathways that are well worth consideration.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program