Manufacturing cycle prediction using structural equation model toward industrial early warning system simulation: The...

Area of Science:

• Economics
• Econometrics
• Economic Forecasting

Background:

• Composite Leading Indices (CLIs) are crucial for economic cycle prediction.
• Existing research often focuses on individual CLIs, potentially limiting predictive accuracy.
• Understanding the interplay of short, medium, and long-term CLIs is vital for robust economic forecasting.

Purpose of the Study:

• To integrate short-term, medium-term, and long-term Composite Leading Indices (CLIs) for enhanced predictive capabilities.
• To investigate the relationships among CLIs for forecasting Indonesia's Manufacturing Cycle (ManC).
• To validate the application of Partial Least Squares-Structural Equation Modeling (PLS-SEM) in ManC forecasting.

Main Methods:

• Utilized quarterly data from Q1 2010 to Q2 2022.
• Employed Partial Least Squares-Structural Equation Modeling (PLS-SEM) for analysis.
• Incorporated five constructs representing key economic sectors influencing the manufacturing cycle, including Short Leading Economic Index (SLEI), International Trade Channel (ITC), Fiscal Cycle (FC), and Monetary Cycle (MC).

Main Results:

• Demonstrated that interconnected CLIs offer enhanced predictive capabilities compared to individual CLIs.
• Successfully forecasted Indonesia's Manufacturing Cycle (ManC) using the integrated CLI approach.
• Validated the effectiveness of PLS-SEM in analyzing complex economic relationships for forecasting.

Conclusions:

• The integration of diverse Composite Leading Indices significantly improves the accuracy of economic cycle forecasting.
• PLS-SEM is a suitable methodology for modeling the intricate relationships within economic indicators to predict the Manufacturing Cycle.
• This study provides a robust framework for utilizing interconnected CLIs in economic policy and planning.