Economics, Econometrics and Finance
8 years ago

New model predicts future trends in multivariate time series data.

Canadian Journal of Statistics
On a mixture vector autoregressive model
Tom Fong, W. K. Li, Christopher W.H. Yau, C. S. Wong

Paper Summary

Related papers

Theme background image
Engineering
2 years ago

New autoregressive models revolutionize forecasting for active energy complexes!

Electricity Forecasting
Stock Market Predictions
Oil Price Shocks
Decision Sciences
2 years ago

Revolutionary Models Predict Future Events with Unprecedented Accuracy

Time Series Forecasting
Theme background image
Computer Science
2 years ago

Non-autoregressive neural networks outperform autoregressive for faster system identification.

Neural Networks
Anomaly Detection
Image Denoising
1 view

The article introduces a new way to analyze multiple time series data by combining different types of autoregressive models. The researchers developed a method to determine when these models are stable over time, and they created a way to estimate the parameters of the models. By testing their method with simulations and real data, they found that it performs well in practice.