International evidence on the predictability of returns to securitized real estate assets: econometric models versus neural networks

The performance of various statistical models and commonly used financial indicators for forecasting securitised real estate returns are examined for five European countries: the UK, Belgium, the Netherlands, France and Italy. Within a VAR framework, it is demonstrated that the gilt-equity yield ratio is in most cases a better predictor of securitized returns than the term structure or the dividend yield. In particular, investors should consider in their real estate return models the predictability of the gilt-equity yield ratio in Belgium, the Netherlands and France, and the term structure of interest rates in France. Predictions obtained from the VAR and univariate time-series models are compared with the predictions of an artificial neural network model. It is found that, whilst no single model is universally superior across all series, accuracy measures and horizons considered, the neural network model is generally able to offer the most accurate predictions for 1-month horizons. For quarterly and half-yearly forecasts, the random walk with a drift is the most successful for the UK, Belgian and Dutch returns and the neural network for French and Italian returns. Although this study underscores market context and forecast horizon as parameters relevant to the choice of the forecast model, it strongly indicates that analysts should exploit the potential of neural networks and assess more fully their forecast performance against more traditional models.

Land re-use, complexity and actor-networks: a framework for research

This paper will present a conceptual framework for the examination of land redevelopment based on a complex systems/networks approach. As Alvin Toffler insightfully noted, modern scientific enquiry has become exceptionally good at splitting problems into pieces but has forgotten how to put the pieces back together. Twenty-five years after his remarks, governments and corporations faced with the requirements of sustainability are struggling to promote an ‘integrated’ or ‘holistic’ approach to tackling problems. Despite the talk, both practice and research provide few platforms that allow for ‘joined up’ thinking and action. With socio-economic phenomena, such as land redevelopment, promising prospects open up when we assume that their constituents can make up complex systems whose emergent properties are more than the sum of the parts and whose behaviour is inherently difficult to predict. A review of previous research shows that it has mainly focused on idealised, ‘mechanical’ views of property development processes that fail to recognise in full the relationships between actors, the structures created and their emergent qualities. When reality failed to live up to the expectations of these theoretical constructs then somebody had to be blamed for it: planners, developers, politicians. However, from a ‘synthetic’ point of view the agents and networks involved in property development can be seen as constituents of structures that perform complex processes. These structures interact, forming new more complex structures and networks. Redevelopment then can be conceptualised as a process of transformation: a complex system, a ‘dissipative’ structure involving developers, planners, landowners, state agencies etc., unlocks the potential of previously used sites, transforms space towards a higher order of complexity and ‘consumes’ but also ‘creates’ different forms of capital in the process. Analysis of network relations point toward the ‘dualism’ of structure and agency in these processes of system transformation and change. Insights from actor network theory can be conjoined with notions of complexity and chaos to build an understanding of the ways in which actors actively seek to shape these structures and systems, whilst at the same time are recursively shaped by them in their strategies and actions. This approach transcends the blame game and allows for inter-disciplinary inputs to be placed within a broader explanatory framework that does away with many past dichotomies. Better understanding of the interactions between actors and the emergent qualities of the networks they form can improve our comprehension of the complex socio-spatial phenomena that redevelopment comprises. The insights that this framework provides when applied in UK institutional investment into redevelopment are considered to be significant.

Approximation of non-autonomous dynamic systems by continuous time recurrent neural networks

This work provides a framework for the approximation of a dynamic system of the form x˙=f(x)+g(x)u by dynamic recurrent neural network. This extends previous work in which approximate realisation of autonomous dynamic systems was proven. Given certain conditions, the first p output neural units of a dynamic n-dimensional neural model approximate at a desired proximity a p-dimensional dynamic system with n>p. The neural architecture studied is then successfully implemented in a nonlinear multivariable system identification case study.

Inverting recurrent neural networks for internal model control of nonlinear systems

In this paper, we show how a set of recently derived theoretical results for recurrent neural networks can be applied to the production of an internal model control system for a nonlinear plant. The results include determination of the relative order of a recurrent neural network and invertibility of such a network. A closed loop controller is produced without the need to retrain the neural network plant model. Stability of the closed-loop controller is also demonstrated.

A practical approach for training dynamic recurrent neural networks: use of Apriori information

Presents a technique for incorporating a priori knowledge from a state space system into a neural network training algorithm. The training algorithm considered is that of chemotaxis and the networks being trained are recurrent neural networks. Incorporation of the a priori knowledge ensures that the resultant network has behaviour similar to the system which it is modelling.

Multiple PID mapping using neural networks in a MIMO steam generator system

A neural network was used to map three PID operating regions for a two-input two-output steam generator system. The network was used in stand alone feedforward operation to control the whole operating range of the process, after being trained from the PID controllers corresponding to each control region. The network inputs are the plant error signals, their integral, their derivative and a 4-error delay train.

Internal model control of nonlinear systems through the inversion of recurrent neural networks

Recurrent neural networks can be used for both the identification and control of nonlinear systems. This paper takes a previously derived set of theoretical results about recurrent neural networks and applies them to the task of providing internal model control for a nonlinear plant. Using the theoretical results, we show how an inverse controller can be produced from a neural network model of the plant, without the need to train an additional network to perform the inverse control.

Multi-layer radial basis function networks: an extension to the radial basis function

This paper presents the initial research carried out into a new neural network called the multilayer radial basis function network (MRBF). The network extends the radial basis function (RBF) in a similar way to that in which the multilayer perceptron extends the perceptron. It is hoped that by connecting RBFs together in a layered fashion, an equivalent increase in ability can be gained, as is gained from using MLPs instead of single perceptrons. The results of a practical comparison between individual RBFs and MRBF's are also given.

Dynamic input/output linearization using recurrent neural networks

A dynamic recurrent neural network (DRNN) is used to input/output linearize a control affine system in the globally linearizing control (GLC) structure. The network is trained as a part of a closed loop that involves a PI controller, the goal is to use the network, as a dynamic feedback, to cancel the nonlinear terms of the plant. The stability of the configuration is guarantee if the network and the plant are asymptotically stable and the linearizing input is bounded.