For the evaluation of Web sites, a multitude of metrics are available. Apart from general statistical measures, success metrics reflect the degree to which a Web site achieves its defined objectives. Particularly metrics for e-commerce sites based on transaction analysis are commonly available and well understood. In contrast to transaction based sites, the success of Web sites geared toward information delivery is harder to quantify since there is no direct feedback of user intent. User feedback is only directly available on transactional Web sites. We introduce a metric to measure the success of an information driven Web site in meeting its objective to deliver the desired information in a timely and usable fashion. We propose to assign a value to each click based on the type of transition, duration and semantic distance. These values are then combined into a scoring model describing the success of a Web site in meeting its objectives. The resulting metric is introduced as the GPI and its applicability shown on a large corporate Web site.

This paper deals with a neural network architecture which establishes a portfolio management system similar to the Black / Litterman approach. This allocation scheme distributes funds across various securities or fi- nancial markets while simultaneously complying with specific allocation constraints which meet the requirements of an investor. The portfolio optimization algorithm is modeled by a feedforward neural network. The underlying expected return forecasts are based on error correction neural networks (ECNN), which utilize the last model error as an auxiliary input to evaluate their own misspecification. The portfolio optimization is implemented such that (i.) the allocations comply with investor’s constraints and that (ii.) the risk of the portfo- lio can be controlled. We demonstrate the profitability of our approach by constructing internationally diversified portfolios across
 different financial markets of the G7 contries. It turns out, that our approach is superior to a preset benchmark portfolio. 1 Introduction: Portfolio-Management We integrate the portfolio optimization algorithm suggested by Black / Litterman [1] into a neural network architecture. Combining the mean-variance theory [5] with the capital asset pricing model (CAPM) [7], this approach utilizes excess returns of the CAPM equilibrium to define a neutral, well balanced benchmark portfolio. Deviations from the benchmark allocation are only allowed within preset boundaries. Hence, as an advantage, there are no unrealistic solutions (e. g. large short positions, huge portfolio changes). Moreover, there is no need of formulating return expectations for all assets. In contrast to Black / Litterman, excess return forecasts are estimated by time-delay recur- rent error correction neural networks [8]. Investment decisions which comply with given allocation constraints are derived from these predictions. The risk exposure of the portfolio is implicitly controlled by a parameter-optimizing task over time (sec. 3 and 5). Our approach consists of the following three steps: (i.) Construction of forecast models    on the basis of error correction neural networks (ECNN) for all  assets (sec. 2).  To whom correspondence should be addressed: [email protected]. (sec. 3 and 4). By this, the profitability of an asset with respect to all others is measured. (ii.) Computation of excess returns 
 (iii.) Optimization of the investment proportions Allocation constraints ensure, that the investment proportions  by a higher-level feedforward network
on the basis of the excess returns.
may deviate from a given benchmark only within predefined intervals (sec. 3 and 4). Finally, we apply our neural network based portfolio management system to an asset allo- cation problem concerning the G7 countries (sec. 6).
 2 Forecasting by Error Correction Neural Networks Most dynamical systems are driven by a superposition of autonomous development and external influences [8]. For discrete time grids, such a dynamics can be described by a recurrent state transition   and an output equation (Eq. 1).   state transition eq. output eq.

We introduce an explanatory multi-agent approach of multiple FX-market modeling based on neural networks. We consider the explicit and implicit dynamics of the market price. This paper extends previous work of modeling a single FX-market to an integrated approach, which allows one to treat several FX-markets simultaneously. Our approach is based on feedforward neural networks. Neural networks allow the fitting of high-dimensional nonlinear models, which is often utilized in econometrics. Merging the economic theory of multi-agents with neural networks, our model concerns semantic specifications instead of being limited to ad hoc functional relationships. As an advantage, our multi-agent model allows one to fit the behavior of real-world financial data. We exemplify the USD/DEM and YEN/DEM FX-Market simultaneously. Fitting real-world data, our approach is superior to more conventional forecasting techniques.

In this paper a highly robust method to predict symbolic prosody labels for speech synthesis is proposed. This method is based on a two stage approach. In the first stage the characteristics of each symbolic prosody label are captured by autoassociative models, which are trained independently. In the second stage detailed error information obtained from the different autoassociative models is used to train a neural classifier yielding class conditional probabilities. The method has been successfully applied for German and English language. For the latter the exact same data bases as used by Black and Taylor (1997) and Ostendorf and Veilleux (1994) were used to test the method. The results obtained are superior to those reported for the HMM-based and CART-based approaches. Further experiments also demonstrate considerable generalizing ability, yielding high robustness in sparse training material conditions.

We compare the performance of multilayer perceptrons and density estimating neural networks in the task of forecasting the return and the volatility of the DAX index. We claim that for nontrivial target distributions, density estimating networks should lead to improved predictions. The reason is that the latter are capable of embodying more complex probability models for the target noise. We discuss appropriate distribution assumptions for the important cases of outliers and non constant variances, and give interpretations of the new estimates in regression theory.

We present efficient algorithms for dealing with the problem of mis(cid:173) sing inputs (incomplete feature vectors) during training and recall. Our approach is based on the approximation of the input data dis(cid:173) tribution using Parzen windows. For recall, we obtain closed form solutions for arbitrary feedforward networks. For training, we show how the backpropagation step for an incomplete pattern can be approximated by a weighted averaged backpropagation step. The complexity of the solutions for training and recall is independent of the number of missing features. We verify our theoretical results using one classification and one regression problem.