Christoph Tietz

Forecasting with Recurrent Neural Networks: 12 Tricks

Recurrent neural networks (RNNs) are typically considered as relatively simple architectures, which come along with complicated learning algorithms. This paper has a different view: We start from the fact that RNNs can model any high dimensional, nonlinear dynamical system. Rather than focusing on learning algorithms, we concentrate on the design of network architectures. Unfolding in time is a well-known example of this modeling philosophy. Here a temporal algorithm is transferred into an architectural framework such that the learning can be performed by an extension of standard error backpropagation.

Market Modeling, Forecasting and Risk Analysis with Historical Consistent Neural Networks

Business management requires precise forecasts in order to enhance the quality of planning throughout the value chain. Furthermore, the uncertainty in forecasting has to be taken into account.

Forecasting Market Prices with Causal-Retro-Causal Neural Networks

Forecasting of market prices is a basis of rational decision making [Zim94]. Especially recurrent neural networks (RNN) offer a framework for the computation of a complete temporal development. Our applications include short- (20 days) and long-term (52 weeks) forecast models. We describe neural networks (NN) along a correspondence principle, representing them in form of equations, architectures and embedded local algorithms.

Historical Consistent Neural Networks: New Perspectives on Market Modeling, Forecasting and Risk Analysis

From a mathematical point of view, neural networks allow the construction of models, which are able to handle high-dimensional problems along with a high degree of nonlinearity. In this chapter we deal with a special type of time-delay recurrent neural networks. In these models we understand a part of the world as a large recursive system which is only partially observable. We model and forecast all observables, avoiding the problem in open systems that we do not know the external drivers from present time on. This framework goes far beyond the paradigms of standard regression theory and allows us to forecast financial markets and perform a new way of risk analysis.

Recurrent Neural Networks for Industrial Procurement Decisions

Rational decisions are based upon forecasts. Precise forecasting has therefore a central role in business. The prediction of commodity prices or the prediction of energy load curves are prime examples. We introduce recurrent neural networks to model economic or industrial dynamic systems.

A technical trading indicator based on dynamical consistent neural networks

In econometrics, the behaviour of financial markets is described by quantitative variables. Mathematical and statistical methods are used to explore economic relationships and to forecast the future market development. However, econometric modeling is often limited to a single financial market. In the age of globalisation financial markets are highly interrelated and thus, single market analyses are misleading. In this paper we present a new way to model the dynamics of coherent financial markets. Our approach is based on so-called dynamical consistent neural networks (DCNN), which are able to map multiple scales and different sub-dynamics of the coherent market movement. Unlikely to standard econometric methods, small market movements are not treated as noise but as valuable market information. We apply the DCNN to forecast monthly movements of major foreign exchange (FX) rates. Based on the DCNN forecasts we develop a technical trading indicator to support investment decisions.

Market Modeling Based on Cognitive Agents

In this paper, we present an explanatory multi-agent model. The agents decision making is based on cognitive systems with three basic features (perception, internal processing and action). The interaction of the agents allows us to capture the market dynamics.The three features are derived deductively from the assumption of homeostasis and constitute necessary conditions of a cognitive system. Given a changing environment, homeostasis can be seen as the attempt of a cognitive agent to maintain an internal equilibrium. We model the cognitive system with a time-delay recurrent neural network.We apply our approach to the DEM / USD FX-Market. Fitting realworld data, our approach is superior to a preset benchmark (MLP).

SESAME — A software environment for combining multiple neural network paradigms and applications

Abstract We developed SESAME to make complex experiments possible, that combine different neural network and learning paradigms in an elegant way. SESAME represents an object-oriented framework in which experiments are constructed by uniform building blocks. Experiment substructures can be integrated at any place. Examples are given for Back-propagation and Feature Maps.