Estimating Parameters for Technology Investments: An Application to 3d Printing

Abstract

One of the major limiting factors and criticism about the real options approach is related to issues with estimating the right input values for state variables that are critical to make the right investment decisions under uncertainty. While vast research exists that applies real options valuation to technology investments, scholars often present theoretical findings based on fictional numerical applications neglecting the process of estimating the right input variables for their models. We present a simple framework to obtain these variables for technology investments by analysing publicly available data such as bibliometrics and patents related to any technology and apply it to forecast 3D printing technology diffusion. We base our approach on the Bass model, which is a prominent technique in the area of technology forecasting and show that these methods can help to forecast technology diffusion and obtain the required input parameters for technology investment decisions. We further use our 3D printing example to demonstrate the major differences between the suggested technology diffusion model and a standard Geometric Brownian Motion (GBM) model, as it is often found in Real Options literature. We find that the GBM is often not suitable when analysing technology investments, as it can lead to wrong investment decisions.