Early Warning Software for Emergency Department Crowding.

Emergency department (ED) crowding is a well-recognized threat to patient safety and it has been repeatedly associated with increased mortality. Accurate forecasts of future service demand could lead to better resource management and has the potential to improve treatment outcomes. This logic has motivated an increasing number of research articles but there has been little to no effort to move these findings from theory to practice. In this article, we present first results of a prospective crowding early warning software, that was integrated to hospital databases to create real-time predictions every hour over the course of 5 months in a Nordic combined ED using Holt-Winters' seasonal methods. We show that the software could predict next hour crowding with an AUC of 0.94 (95% CI: 0.91-0.97) and 24 hour crowding with an AUC of 0.79 (95% CI: 0.74-0.84) using simple statistical models. Moreover, we suggest that afternoon crowding can be predicted at 1 p.m. with an AUC of 0.84 (95% CI: 0.74-0.91).

Prognostic modeling of predictive maintenance with survival analysis for mobile work equipment.

In recent years there is a data surge of industrial and business data. This posses opportunities and challenges at the same time because the wealth of information is usually buried in complex and frequently disconnected data sets. Predictive maintenance utilizes such data for developing prognostic and diagnostic models that allow the optimization of the life cycle of machine components. In this paper, we address the modeling of the prognostics of machine components from mobile work equipment. Specifically, we are estimating survival curves and hazard rates using parametric and non-parametric models to characterize time dependent failure probabilities of machine components. As a result, we find the presence of different types of censoring masking the presence of different populations that can cause severe problems for statistical estimators and the interpretations of results. Furthermore, we show that the obtained hazard functions for different machine components are complex and versatile and are best modeled via non-parametric estimators. However, notable exceptions for individual machine components can be found amenable for a Generalized-gamma and Weibull model.

Structure of Investor Networks and Financial Crises.

In this paper, we ask whether the structure of investor networks, estimated using shareholder registration data, is abnormal during a financial crises. We answer this question by analyzing the structure of investor networks through several most prominent global network features. The networks are estimated from data on marketplace transactions of all publicly traded securities executed in the Helsinki Stock Exchange by Finnish stock shareholders between 1995 and 2016. We observe that most of the feature distributions were abnormal during the 2008-2009 financial crisis, with statistical significance. This paper provides evidence that the financial crisis was associated with a structural change in investors' trade time synchronization. This indicates that the way how investors use their private information channels changes depending on the market conditions.

Mid-price prediction based on machine learning methods with technical and quantitative indicators.

Stock price prediction is a challenging task, in which machine learning methods have recently been successfully used. In this paper, we extract over 270 hand-crafted features (factors) inspired by technical indicators and quantitative analysis and test their validity on short-term mid-price movement prediction for Nordic TotalView-ITCH stocks. The suggested feature list represents one of the most extensive studies in the field of financial feature engineering. We focus on a wrapper feature selection method using entropy, least-mean squares, and linear discriminant analysis. We also introduce a novel quantitative feature based on adaptive logistic regression for online learning. The proposed feature is consistently selected as the first feature among a large number of indicators used in this study. We further examine the best combinations of features using a high-frequency limit order book Nordic database. Our results suggest that sorting methods and classifiers can be used in such a way that one can reach the best classification performance with a combination of only a few advanced hand-crafted features.

Deep Adaptive Input Normalization for Time Series Forecasting.

Deep learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when DL is used for financial time series forecasting tasks, where the nonstationary and multimodal nature of the data pose significant challenges and severely affect the performance of DL models. In this brief, a simple, yet effective, neural layer that is capable of adaptively normalizing the input time series, while taking into account the distribution of the data, is proposed. The proposed layer is trained in an end-to-end fashion using backpropagation and leads to significant performance improvements compared to other evaluated normalization schemes. The proposed method differs from traditional normalization methods since it learns how to perform normalization for a given task instead of using a fixed normalization scheme. At the same time, it can be directly applied to any new time series without requiring retraining. The effectiveness of the proposed method is demonstrated using a large-scale limit order book data set, as well as a load forecasting data set.

Temporal Attention-Augmented Bilinear Network for Financial Time-Series Data Analysis.

Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market. In the high-frequency trading, forecasting for trading purposes is even a more challenging task, since an automated inference system is required to be both accurate and fast. In this paper, we propose a neural network layer architecture that incorporates the idea of bilinear projection as well as an attention mechanism that enables the layer to detect and focus on crucial temporal information. The resulting network is highly interpretable, given its ability to highlight the importance and contribution of each temporal instance, thus allowing further analysis on the time instances of interest. Our experiments in a large-scale limit order book data set show that a two-hidden-layer network utilizing our proposed layer outperforms by a large margin all existing state-of-the-art results coming from much deeper architectures while requiring far fewer computations.

Dynamics of investor spanning trees around dot-com bubble.

We identify temporal investor networks for Nokia stock by constructing networks from correlations between investor-specific net-volumes and analyze changes in the networks around dot-com bubble. The analysis is conducted separately for households, financial, and non-financial institutions. Our results indicate that spanning tree measures for households reflected the boom and crisis: the maximum spanning tree measures had a clear upward tendency in the bull markets when the bubble was building up, and, even more importantly, the minimum spanning tree measures pre-reacted the burst of the bubble. At the same time, we find less clear reactions in the minimal and maximal spanning trees of non-financial and financial institutions around the bubble, which suggests that household investors can have a greater herding tendency around bubbles.

Multilayer Aggregation with Statistical Validation: Application to Investor Networks.

Multilayer networks are attracting growing attention in many fields, including finance. In this paper, we develop a new tractable procedure for multilayer aggregation based on statistical validation, which we apply to investor networks. Moreover, we propose two other improvements to their analysis: transaction bootstrapping and investor categorization. The aggregation procedure can be used to integrate security-wise and time-wise information about investor trading networks, but it is not limited to finance. In fact, it can be used for different applications, such as gene, transportation, and social networks, were they inferred or observable. Additionally, in the investor network inference, we use transaction bootstrapping for better statistical validation. Investor categorization allows for constant size networks and having more observations for each node, which is important in the inference especially for less liquid securities. Furthermore, we observe that the window size used for averaging has a substantial effect on the number of inferred relationships. We apply this procedure by analyzing a unique data set of Finnish shareholders during the period 2004-2009. We find that households in the capital have high centrality in investor networks, which, under the theory of information channels in investor networks suggests that they are well-informed investors.