Video activity extraction and reporting with incremental unsupervised learning

The present work presents a new method for activity extraction and reporting from video based on the aggregation of fuzzy relations. Trajectory clustering is first employed mainly to discover the points of entry and exit of mobiles appearing in the scene. In a second step, proximity relations between resulting clusters of detected mobiles and contextual elements from the scene are modeled employing fuzzy relations. These can then be aggregated employing typical soft-computing algebra. A clustering algorithm based on the transitive closure calculation of the fuzzy relations allows building the structure of the scene and characterises the ongoing different activities of the scene. Discovered activity zones can be reported as activity maps with different granularities thanks to the analysis of the transitive closure matrix. Taking advantage of the soft relation properties, activity zones and related activities can be labeled in a more human-like language. We present results obtained on real videos corresponding to apron monitoring in the Toulouse airport in France.

The role of competition and state aid policy in financial and monetary law

During the financial crisis, companies and lenders found themselves in distressed situations. Competition authorities across the globe had to deal with controversial issues such as the application of the failing firm defence in merger transactions as well as assessment of emergency aid granted by states. This article considers competition policy in periods of crisis, in particular the failing firm defence in merger control and its state aid policy.

On the utility of input selection and pruning for financial distress prediction models

Analyzes the use of linear and neural network models for financial distress classification, with emphasis on the issues of input variable selection and model pruning. A data-driven method for selecting input variables (financial ratios, in this case) is proposed. A case study involving 60 British firms in the period 1997-2000 is used for illustration. It is shown that the use of the Optimal Brain Damage pruning technique can considerably improve the generalization ability of a neural model. Moreover, the set of financial ratios obtained with the proposed selection procedure is shown to be an appropriate alternative to the ratios usually employed by practitioners.

Systematic property risk: quantifying UK property betas 1983-2005

The increased frequency in reporting UK property performance figures, coupled with the acceptance of the IPD database as the market standard, has enabled property to be analysed on a comparable level with other more frequently traded assets. The most widely utilised theory for pricing financial assets, the Capital Asset Pricing Model (CAPM), gives market (systematic) risk, beta, centre stage. This paper seeks to measure the level of systematic risk (beta) across various property types, market conditions and investment holding periods. This paper extends the authors’ previous work on investment holding periods and how excess returns (alpha) relate to those holding periods. We draw on the uniquely constructed IPD/Gerald Eve transactions database, containing over 20,000 properties over the period 1983-2005. This research allows us to confirm our initial findings that properties held over longer periods perform in line with overall market performance. One implication of this is that over the long-term performance may be no different from an index tracking approach.

The impact of country risk on international real estate returns

Commercial real estate investors have well-established methods to assess the risks of a property investment in their home country. However, when the investment decision is overseas another dimension of uncertainty overlays the analysis. This additional dimension, typically called country risk, encompasses the uncertainty of achieving expected financial results solely due to factors relating to the investment’s location in another country. However, very little has been done to examine the effects of country risk on international real estate returns, even though in international investment decisions considerations of country risk dominate asset investment decisions. This study extends the literature on international real estate diversification by empirically estimating the impact of country risk, as measured by Euromoney, on the direct real estate returns of 15 countries over the period 1998-2004, using a pooled regression analysis approach. The results suggest that country risk data may help investor’s in their international real estate decisions since the country risk data shows a significant and consistent impact on real estate return performance.

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.