Investment decisions modeled by neural net detecting technology patterns
The Investment Acceleration Principle Revisited by means of a Neural Network
Neural and Evolutionary Computing
Summary
Investing money in new projects often depends on how companies see changes in technology. The authors created a model that uses a special kind of artificial intelligence called a Kohonen neural network to understand when managers decide to invest. This model treats investments as reactions to recognizing emerging technological trends. It also separates investments driven by innovation from those made to copy existing facilities.
What this means in practice
- •For economic modelers: Incorporate AI-based pattern recognition in investment time series models to better differentiate innovation-related investments from routine expansions.
- •For corporate finance teams: Use neural network insights to anticipate which technological changes prompt managerial investment decisions for strategic financial planning.
Authors
Guido Fioretti
Abstract
The investment acceleration principle is a heuristic for modelling investment time series out of consumption time series. The model presented herein develops a disaggregated accelerator equation whose coefficients are the weights of a Kohonen neural net that represents firms' decision-making. According to this model, investments take place when managers recognise emerging technological patterns. Furthermore, a technique borrowed from the theory of self-organising systems is used in order to disentangle innovation-driven investments from plant-replication investments.