Assessing market penetration combining scenario analysis, Delphi, and the technological substitution model: The case of the OLED TV market

The technological substitution model, proposed in 1971, was designed to analyze the penetration process of new-generation technologies replacing old ones. It was expanded in 1979 to consider more than two generations and the substitution process among various entities in the market. However, this expanded model is often limited by a relative lack of data on the latest-generation technology.On the other hand, scenario analysis, as another breed to forecasting tool, provides rich and complex portraits of possible future development of technologies. However, it fails to provide quantifiable forecasts. Therefore, previous researchers combined these two methods to analyze the development of new technologies.Nevertheless, to make forecasting more holistic, the current opinions of seasoned experts should also be taken into account. However, because of the often-diverged expert opinions, a method for consensus building, such as the Delphi method, is also necessary. Therefore, we combined the scenario analysis with the Delphi method and the technological substitution model to analyze the development of a new technology, namely, the latest-generation television (TV), or the organic light-emitting diode (OLED) TV. We elaborate three possible scenarios, and forecast the market share of OLED TV and four other TV technologies in the global market over the next 10 years: cathode ray tube, rear projection, plasma display panel, and liquid crystal display.     

A model for forecasting the substitution of one technology for another

Most technological changes can be described as a substitution of one material, process or product for another. Each such substitution, if successful, normally tends to follow an S-shaped (or “logistic”) curve: that is, it starts slowly as initial problems and resistances have to be overcome; then it proceeds more rapidly as the competition between the new and the old technology grows keener and the new technology gains an advantage; and finally, as the market for the new technology approaches saturation, the pace of substitution slows down. Sometimes, when the process is completed, the old technology continues to retain some specialized portion of the total market (i.e., a sub-market) for which it is particularly well adapted. In forecasting the course and speed of the substitution process especially when it has already begun and partially taken place, the simplest approach is to project a function having the appropriate S-shaped curve, using historical data to determine the free parameters of the function. While useful, especially where data are not available for a more sophisticated study, the simple curve-fitting techniques fail to take into account several important factors that affect economic and management decisions on the part of producers and intermediate users (as well as “final” consumers) and thereby influence the course which the substitution process is likely to take. To overcome this limitation, a simulation model has been developed at IR&T which allows some of these factors to be evaluated and incorporated explicitly and quantitatively. The model is described and its application is illustrated in the case of the substitution of plastic for glass in bottles. It is most applicable where the competing technologies are rather precisely defined, where a good deal of current technical and economic data are available, and where an in-depth analysis is desired. Because this particular forecast was made before the sudden precipitous increase in petroleum prices, which upsets the price relationships assumed in the forecast, there is discussion of the vulnerability of forecasts to political and other contra-economic developments.     

Problems of forecasting and technology assessment

A broad appraisal of forecasts of U.S. national trends in population, economics, transportation, energy-use, and technology reveals some of the limitations of forecasting and some avenues for improvement. The development of greater methodological sophistication has not significantly improved forecast accuracy. The (often linear) deterioration of accuracy with lengthening of forecast time horizons proceeds regardless of method. Methodology expresses (and traces the implications of) core assumptions reflecting the forecasters' fundamental outlook. Sophisticated methodology cannot save a forecast based on faulty core assumptions.High inaccuracy results from the persistence of out-of-date core assumptions (“assumption drag”), caused by overspecialization, wishful thinking, the infrequency of forecast studies (due to the common preference for expensive approaches), and the weakness of sociopolitical forecasting. This diagnosis calls for more frequent, less elaborate, and interdisciplinary forecasting efforts.Sociopolitical forecasting, required both as a source of core assumptions for projecting other trends and to trace the social impact component of technology assessments, has suffered from a lack of specificity and meaningfulness. The greater uncertainty in forecasting technological developments requiring political decisions and large-scale programs indicates the importance of improving sociopolitical analysis. The social-indicators and scenario approaches are two means for achieving this improvement. Their potential contributions, as well as limitations, are reviewed.     

Forecasting UK consumer price inflation using inflation forecasts

The inflation rate is a key economic indicator for which forecasters are constantly seeking to improve the accuracy of predictions, so as to enable better macroeconomic decision making. Presented in this paper is a novel approach which seeks to exploit auxiliary information contained within inflation forecasts for developing a new and improved forecast for inflation by modeling with Multivariate Singular Spectrum Analysis (MSSA). Unlike other forecast combination techniques, the key feature of the proposed approach is its use of forecasts, i.e. data into the future, within the modeling process and extracting auxiliary information for generating a new and improved forecast. We consider real data on consumer price inflation in UK, obtained via the Office for National Statistics. A variety of parametric and nonparametric models are then used to generate univariate forecasts of inflation. Thereafter, the best univariate forecast is considered as auxiliary information within the MSSA model alongside historical data for UK consumer price inflation, and a new multivariate forecast is generated. We find compelling evidence which shows the benefits of the proposed approach at generating more accurate medium to long term inflation forecasts for UK in relation to the competing models. Finally, through the discussion, we also consider Google Trends forecasts for inflation within the proposed framework.     

For how long do IMF forecasts of world economic growth stay up-to-date?

This study analyses the performance of the International Monetary Fund (IMF) World Economic Outlook output forecasts for the world and for both the advanced economies and the emerging and developing economies. With a focus on the forecast for the current year and the next year, we examine the durability of IMF forecasts, looking at how much time has to pass so that IMF forecasts can be improved by using leading indicators with monthly updates. Using a real-time data set for GDP and for indicators, we find that some simple single-indicator forecasts on the basis of data that are available at higher frequency can significantly outperform the IMF forecasts as soon as the publication of the IMF’s Outlook is only a few months old. In particular, there is an obvious gain using leading indicators from January to March for the forecast of the current year.     

Scenario development for an evolving health insurance industry in rural India: INPUT for business model innovation

The article discusses the use of Delphi-based scenarios for the development of business model innovations in emerging markets. Motivated by insights from information processing and institutional theory we present a scenario development process combining a PEST (political, economic, socio-cultural, and technological) and a stakeholder approach. We exemplify its use for the evolving health insurance market in rural India and present how our approach can be used to study possible future developments relevant for business model innovations. Key insights are that NGOs might play a crucial role along with the regulatory support of the Government of India and significant advances in mobile payment technologies.     

Innovation forecasting

Technological forecasting is premised on a certain orderliness of the innovation process. Myriad studies of technological substitution, diffusion, and transfer processes have yielded conceptual models of what matters for successful innovation, but most technological forecasts key on limited empirical measures quite divorced from those innovation process models. We glean a number of concepts from various innovation models, then present an array of bibliometric measures that offer the promise of operationalizing these concepts. Judicious combination of such bibliometrics with other forms of evidence offers an enriched form of technological forecasting we call “innovation forecasting.” This provides a good means to combine technological trends, mapping of technological interdependencies, and competitive intelligence to produce a viable forecast. We illustrate by assessing prospects for ceramic engine technologies.     

Technology forecasting for commodity projections: A case study on the effect of substitution by aluminum on the future demand for copper

This paper deals with the possible use of technology forecasting in commodity projection and, to a lesser extent, in resource allocation for research and development. As a specific example, technology forecasting was used to estimate the effect of substitution of copper by aluminum on the future demand of copper in 1980 and 1990. and to identify a future technology for extracting aluminum from clay; a technology which could be especially useful in the developing countries. Basic predictions were made for functional units of the major common end uses of copper and aluminum in 1980 and 1990, including electrical conductor and heat exchanger applications. The amounts of copper required in each application in 1980 and 1990 were estimated for three substitution scenarios. In the first of these, substitution is assumed to take place according to a logistic type function, resulting in a predicted copper demand of 3.70 million tons in 1980 and 4.91 million tons in 1990. In the second scenario, substitution is assumed to progress at past linear rates, resulting in a predicted copper demand of 4.3 million tons in 1980 and 6.41 million tons in 1990. In the third scenario, no further substitution is assumed, resulting in a predicted copper demand of 4.81 million tons in 1980 and 7.77 million tons in 1990. The effective date of the technology monitoring that produced these predictions is July 1974, and the predictions are current as of the date. The then current forecasts for copper demand made by the U.S. Bureau of Mines and other agencies using compound growth and regression models, corresponded to the unlikely scenario of no further substitution, and therefore needed correction in view of these anticipated technological changes.     

A stochastic patent citation analysis approach to assessing future technological impacts

The anticipation and forecast of technological changes are of vital importance, as technological advances become increasingly fast and complex. What is at the core is identification of the current technologies that will drive technological changes over the coming few years. In this respect, numerous approaches have been devised to assess future technological impacts based on patent citation information, but do not provide a fair reflection of dynamic and idiosyncratic aspects of technological impacts as they are deterministic methods based on simple citation counts. We propose a stochastic patent citation analysis that can assess future technological impacts in a time period of interest by employing the future citation count as a proxy. At the heart of the proposed approach is a Pareto/NBD (Negative Binomial Distribution) model for taking into account the dynamic and idiosyncratic aspects of technological impacts. A patent citation matrix is first constructed for each time unit with citation patterns of the past. The future technological impacts are then derived by Pareto/NBD sub-model and gamma–gamma sub-model. A case study of the display technology patents is presented to illustrate the proposed approach. We believe our method can be employed in various research fields, from narrow patent valuation, to broad technological analysis and planning.     

Assessing and forecasting technology dynamics in smartphones: a TFDEA approach

Over the last 20 years, the smartphone technologies at the device level have undergone tremendous change. This paper puts forward a framework to characterise, assess and forecast the smartphone technologies at the device level. The study assesses and forecasts the technological advancement observed in smartphones using technology forecasting using data envelopment analysis with an objective to evaluate the technological rate of change in the device. A quarterly data set comprising 31 quarters from 2007 to 2014 was analysed for smartphone releases in a particular price range. For the validation purpose, the analysis was designed to set the point of forecasting somewhere in 2012 using the data set between 2007 and 2012, so as to forecast the technologies thereon till 2014. The results indicate that the rate of technological change in smartphones is accelerating.     

A Bayesian method of combining judgmental and model-based density forecasts

This paper introduces a formal method of combining expert and model density forecasts when the sample of past forecasts is unavailable. It works directly with the expert forecast density and endogenously delivers weights for forecast combination, relying on probability rules only. The empirical part of the paper illustrates how the framework can be applied in forecasting US inflation by mixing density forecasts from an autoregressive model and the Survey of Professional Forecasters.     

Forecasting emerging technologies: Use of bibliometrics and patent analysis

It is rather difficult to forecast emerging technologies as there is no historical data available. In such cases, the use of bibliometrics and patent analysis have provided useful data. This paper presents the forecasts for three emerging technology areas by integrating the use of bibliometrics and patent analysis into well-known technology forecasting tools such as scenario planning, growth curves and analogies. System dynamics is also used to be able to model the dynamic ecosystem of the technologies and their diffusion. Technologies being forecasted are fuel cell, food safety and optical storage technologies. Results from these three applications help us to validate the proposed methods as appropriate tools to forecast emerging technologies.     

Alternative methods for developing business scenarios

Recently increasing emphasis is being placed by corporate planners and forecasters on the use of scenario analysis to produce forecasts of future business environments and to identify conditions leading to major changes in these environments. This article compares some of the major approaches to scenario analysis including intuitive logics, trend-impact analysis, and cross-impact analysis. The advantages and disadvantages of each approach are discussed along with case study examples from the key practitioners such as SRI International, The Futures Group, The Center for Futures Research, and Battelle Columbus Division.     

Long-term macroeconometric models: The case of Poland

Long-term forecasts and scenario analysis should be based on macroeconometric models. The core of long-term models is extended by introducing production functions generating potential output. Their specification includes total factor productivity (TFP) being representative of technological progress. It depends on knowledge capital, i.e. human capital, domestic and foreign R&D. Several channels of transfer of foreign R&D can be distinguished.The potential output differs from the effective output, representing final demand, underlying business cycle fluctuations. To study potential disequilibria a system of equations explaining final demand must be established.Thus the long-term macroeconometric model must be a complete model. Its use may cover long-term forecasts and scenario analysis based on model simulations.The paper outlines the above specifications of the long-term model using as example a new model of the Polish economy. The model is medium-sized. It covers demand and supply side, including prices and financial flows. The results of multiplier analysis are shown revealing model feedbacks, including generation of business cycles. The results of its application are shown: long-term forecasts up to the year 2030 as well as scenarios of development of the Polish economy, including recession scenario.     

Detecting and Predicting Forecast Breakdowns

We propose a theoretical framework for assessing whether a forecast model estimated over one period can provide good forecasts over a subsequent period. We formalize this idea by defining a forecast breakdown as a situation in which the out-of-sample performance of the model, judged by some loss function, is significantly worse than its in-sample performance. Our framework, which is valid under general conditions, can be used not only to detect past forecast breakdowns but also to predict future ones. We show that main causes of forecast breakdowns are instabilities in the data-generating process and relate the properties of our forecast breakdown test to those of structural break tests. The empirical application finds evidence of a forecast breakdown in the Phillips' curve forecasts of U.S. inflation, and links it to inflation volatility and to changes in the monetary policy reaction function of the Fed.     

The automobile road to technological change : Diffusion of the automobile as a process of technological substitution

Advancement of the motor vehicle and its production methods is analyzed as a process of technological change. In a broader context, motor vehicles evolved as an integral component of road transportation through a series of interlaced substitutions of old by new technologies. Building on a large number of studies that described technological substitution processes, first it is shown how new energy forms replaced their predecessors and how the old marine-transport technologies were substituted by new ones. These examples constitute some of the oldest, empirically documented technological changes and show that many events in the dynamics of energy substitution and marine transport are related to technological changes in road transportation. It is shown that these substitution processes can be described by simple rules and that the replacement of old by new technologies in the energy and transport systems lasted about 80 years. The technological changes within road transportation, however, were more rapid. Replacement of horses by automobiles and older by newer generations of motor vehicles and production methods lasted only a few decades in the United States. Thus, technological substitutions within the road-transportation system were considerably shorter than the expansion of railroads, surfaced roads, all road vehicles together, and the more recent expansion of air transportation.     

A two factor model to combine US inflation forecasts

The combination of individual forecasts is often a useful tool to improve forecast accuracy. The most commonly used technique for forecast combination is the mean, and it has frequently proved hard to surpass. This study considers factor analysis to combine US inflation forecasts showing that just one factor is not enough to beat the mean and that the second one is necessary. The first factor is usually a weighted mean of the variables and it can be interpreted as a consensus forecast, while the second factor generally provides the differences among the variables and, since the observations are forecasts, it may be related with the dispersion in forecasting expectations and, in a sense, with its uncertainty. Within this approach, the study also revisits Friedman's hypothesis relating the level of inflation with expectations uncertainty at the beginning of the twenty-first century.     

Generalized Lotka-Volterra equations and the mechanism of technological substitution

This paper demonstrates that if technological substitution is viewed as the result of competition between old and new technology in which new technology wins, and if generalized Lotka-Volterra equations are taken to describe this competition, then various models of technological substitution can be obtained as very special cases. It is argued that this could lead to a better understanding of the substitution process itself.     

IMPROVING FORECAST ACCURACY BY COMBINING RECURSIVE AND ROLLING FORECASTS*

This article presents analytical, Monte Carlo, and empirical evidence on combining recursive and rolling forecasts when linear predictive models are subject to structural change. Using a characterization of the bias–variance trade‐off faced when choosing between either the recursive and rolling schemes or a scalar convex combination of the two, we derive optimal observation windows and combining weights designed to minimize mean square forecast error. Monte Carlo experiments and several empirical examples indicate that combination can often provide improvements in forecast accuracy relative to forecasts made using the recursive scheme or the rolling scheme with a fixed window width.