Activity Number:
|
350
- New Methods for Time Series and Longitudinal Data
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
Abstract #304352
|
|
Title:
|
Recurrent Neural Networks for ARMA Model Selection
|
Author(s):
|
Bei Chen* and Beat Buesser and Kelsey DiPietro
|
Companies:
|
IBM Research and IBM Research and University of Notre Dame
|
Keywords:
|
RNN;
Time Series;
Model Selection;
Networks;
DL;
Forecasting
|
Abstract:
|
Selecting an appropriate ARMA model for a given time series is a classic problem in statistics that is encountered in many applications. Typically, this involves a human-in-the-loop and repeated parameter evaluation of candidate models, which is not ideal for learning at scale. We propose a Long Short Term Memory (LSTM) classification model for automatic ARMA model selection. Our numerical experiments show that the proposed method is fast and provides better accuracy than the traditional Box-Jenkins approach based on autocorrelations and model selection criteria. We demonstrate the application of our approach with a case study on volatility prediction of daily stock prices.
|
Authors who are presenting talks have a * after their name.