Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enhancing the Accuracy of Regional Input-Output Table Estimation: A Deep Learning Approach

Shogo Fukui

Abstract

Non-survey methods have been developed and applied for estimating regional input-output tables. However, there is an ongoing debate about the assumptions necessary for these methods and their accuracy. To address these issues, this study presents a deep learning method for estimating regional input-output tables. First, the quantitative economic data for regions is augmented by linear combinations. Then, deep learning is performed on each item in the input-output table, treating these items as target variables. Finally, regional input-output tables are estimated through matrix balancing to the predicted values from the trained model. The estimation accuracy of this method is verified using the 2015 input-output table for Japan as a benchmark. Compared to matrix balancing under the ideal assumption of known row and column sums, our method generally demonstrates higher estimation accuracy. Thus, this method is anticipated to provide a foundation for deriving more precise estimates of regional input-output tables.

Enhancing the Accuracy of Regional Input-Output Table Estimation: A Deep Learning Approach

Abstract

Non-survey methods have been developed and applied for estimating regional input-output tables. However, there is an ongoing debate about the assumptions necessary for these methods and their accuracy. To address these issues, this study presents a deep learning method for estimating regional input-output tables. First, the quantitative economic data for regions is augmented by linear combinations. Then, deep learning is performed on each item in the input-output table, treating these items as target variables. Finally, regional input-output tables are estimated through matrix balancing to the predicted values from the trained model. The estimation accuracy of this method is verified using the 2015 input-output table for Japan as a benchmark. Compared to matrix balancing under the ideal assumption of known row and column sums, our method generally demonstrates higher estimation accuracy. Thus, this method is anticipated to provide a foundation for deriving more precise estimates of regional input-output tables.
Paper Structure (6 sections, 12 equations, 6 figures, 10 tables)

This paper contains 6 sections, 12 equations, 6 figures, 10 tables.

Table of Contents

  1. Introduction
  2. Data and method
  3. Result
  4. Discussion
  5. An overview of the matrix balancing using cross-entropy maximization
  6. Adknowledgments

Figures (6)

  • Figure 1: The neural network model employed in this study
  • Figure 2: Prediction errors (millions of yen) and error rates (%) for each item in the input--output table for Japan. Each cell represents an absolute value. Items without published values are left blank
  • Figure 3: Bar plot of prediction error rates for each item in the input--output table for Japan. Note that the rightmost bar represents the frequency of items with error rates greater than or equal to 100%, while the leftmost bar represents the frequency with error rates less than or equal to 100%
  • Figure 4: Levels of difference (millions of yen) and difference rates (%) between estimates and published values for each item in the input--output tables for Sapporo City. Each cell represents an absolute value. Items without published values are left blank
  • Figure 5: Levels of difference (millions of yen) and difference rates (%) between estimates and published values for each item in the input--output tables for Gujo City. Each cell represents an absolute value. Items without published values are left blank
  • ...and 1 more figures