Search results

This paper aims to replicate 148 anomalies and to examine whether the performance of the Korean market anomalies is statistically and economically significant. First, the authors observe that only 37.8% anomalies in the universe of the KOSPI and the KOSDAQ and value-weighted portfolios have t-statistics that exceed 1.96. When the authors impose a higher threshold (an absolute value of t-statistics of 2.78), only 27.7% of the 148 anomalies survive. Second, microcaps have large impacts. The results vary significantly depending on whether the sample included stocks in the KOSDAQ and whether value-weighted or equal-weighted portfolios are used. The results suggest that data mining explains large portion of abnormal returns. Any tactical asset allocation strategies based on market anomalies should be applied very cautiously.

Transient climate sensitivity relates total climate forcings from anthropogenic and other sources to surface temperature. Global transient climate sensitivity is well studied, as are the related concepts of equilibrium climate sensitivity (ECS) and transient climate response (TCR), but spatially disaggregated local climate sensitivity (LCS) is less so. An energy balance model (EBM) and an easily implemented semiparametric statistical approach are proposed to estimate LCS using the historical record and to assess its contribution to global transient climate sensitivity. Results suggest that areas dominated by ocean tend to import energy, they are relatively more sensitive to forcings, but they warm more slowly than areas dominated by land. Economic implications are discussed.

Several studies have observed that stocks tend to drop by an amount that is less than the dividend on the ex-dividend day, the so-called ex-dividend day anomaly. However, there still remains a lack of consensus for a single explanation of this anomaly. Different from other studies, this dissertation attempts to answer the primary research question: how can investors make trading profits from the ex-dividend day anomaly and how much can they earn? With this goal, I examine the economic motivations of equity investors through four main hypotheses identified in the anomaly's literature: the tax differential hypothesis, the short-term trading hypothesis, the tick size hypothesis, and the leverage hypothesis.

While the U.S. ex-dividend anomaly is well studied, I examine a long data window (1975–2010) of Thailand data. The unique structure of the Thai stock market allows me to assess all four main hypotheses proposed in the literature simultaneously. Although I extract the sample data from two data sources, I demonstrate that the combined data are consistently sampled. I further construct three trading strategies – “daily return,” “lag one daily return,” and “weekly return” – to alleviate the potential effect of irregular data observation.

I find that the ex-dividend day anomaly exists in Thailand, is governed by the tax differential, and is driven by short-term trading activities. That is, investors trade heavily around the ex-dividend day to reap the benefits of the tax differential. I find mixed results for the predictions of the tick size hypothesis and results that are inconsistent with the predictions of the leverage hypothesis.

I conclude that, on the Stock Exchange of Thailand, juristic and foreign investors can profitably buy stocks cum-dividend and sell them ex-dividend while local investors should engage in short sale transactions. On average, investors who employ the daily return strategy have earned significant abnormal return up to 0.15% (45.66% annualized rate) and up to 0.17% (50.99% annualized rate) for the lag one daily return strategy. Investors can also make a trading profit by conducting the weekly return strategy and earn up to 0.59% (35.67% annualized rate), on average.

Most residential building owners often report problems associated with the plumbing systems. If identified at the early stages, plumbing-related defects can be easily repaired. However, if unnoticed for a long period of time, they could lead to major damages and incur a significant cost to repair. Despite the problems, studies investigating plumbing anomalies and their root causes in residential buildings are limited. This study aims to explore plumbing defects and their potential causes, diagnosis methods and repair techniques in residential buildings.

This research used data collected through an extensive survey of both academic and grey literature. Through the content analysis, plumbing defects and the associated causes have been identified and presented in tabular format.

The study investigated the anomalies and causes in the residential plumbing system under five key sub-systems: water supply system; sanitary plumbing system; roof drainage system; heating, ventilation, air conditioning and gas system; and swimming pool. Accordingly, some of the identified plumbing defects include leakages, corrosion, water penetration, slow drainage and cracks. Damaged pipes, faulty equipment and installations are some of the common causes of the anomalies. Visual inspection, hydrostatic pressure test, thermography, high-tech pipe cameras, infrared cameras, leak noise correlators and leak loggers are techniques used for diagnosing anomalies. Reactive, preventive, predictive and reliability-centred maintenance strategies are identified to control or prevent anomalies.

The findings of this research can be used as a useful tool or guideline for contractors, plumbers, facilities managers and building surveyors to identify and rectify plumbing system-related defects in residential buildings.

The purpose of this paper is to detect abnormal data of complex and sophisticated industrial equipment with sensors quickly and accurately. Due to the rapid development of the Internet of Things, more and more equipment is equipped with sensors, especially more complex and sophisticated industrial equipment is installed with a large number of sensors. A large amount of monitoring data is quickly collected to monitor the operation of the equipment. How to detect abnormal data quickly and accurately has become a challenge.

In this paper, the authors propose an approach called Multiple Group Correlation-based Anomaly Detection (MGCAD), which can detect equipment anomaly quickly and accurately. The single-point anomaly degree of equipment and the correlation of each kind of data sequence are modeled by using multi-group correlation probability model (a probability distribution model which is helpful to the anomaly detection of equipment), and the anomaly detection of equipment is realized.

The simulation data set experiments based on real data show that MGCAD has better performance than existing methods in processing multiple monitoring data sequences.

The MGCAD method can detect abnormal data quickly and accurately, promote the intelligent level of smart articles and ultimately help to project the real world into cyber space in CrowdIntell Network.

The purpose of this paper is to test prominent calendar anomalies for Indian securities markets those are commonly reported for advanced markets.

The study considers closing values of 11 different indices of National Stock Exchange India, for the period 1994-2014. By using dummy variable regression technique, five different calendar anomalies namely day of the week effect, month of the year effect, mid-year effect, Halloween effect, and trading-month effect are tested. Also, the evidence of volatility clustering has been tested through the application of generalized autoregressive conditional heteroscedasticity (GARCH)-M models.

The results display weak evidence in support of a positive Wednesday effect. The results also display weak evidence in support of a positive April and December effect. The results show strong evidence in support of a positive September effect. The Halloween effect was not found significant. The test of mid-year effect provides evidence that the returns obtained on the second-half or the year are considerably higher than those obtained during the first half. The test of interactions effects showed possible presence of interactions among various effects. The GARCH-based tests display strong evidence in support of volatility clustering.

The results have several implications for investors, regulators, and researchers. For investors, the trading strategies based on results obtained have been discussed. Similarly, certain key implications for regulators have been described.

The originality of the paper lies in the long time frame and multiple indices covered. Also, the study analyses five different calendar anomalies and the interactions among these effects. These analyses provide useful insights regarding returns predictability for the Indian securities markets.

This study aims to address the challenge of training a detection model for the robot to detect the abnormal samples in the industrial environment, while abnormal patterns are very rare under this condition.

The authors propose a new model with double encoder–decoder (DED) generative adversarial networks to detect anomalies when the model is trained without any abnormal patterns. The DED approach is used to map high-dimensional input images to a low-dimensional space, through which the latent variables are obtained. Minimizing the change in the latent variables during the training process helps the model learn the data distribution. Anomaly detection is achieved by calculating the distance between two low-dimensional vectors obtained from two encoders.

The proposed method has better accuracy and F1 score when compared with traditional anomaly detection models.

A new architecture with a DED pipeline is designed to capture the distribution of images in the training process so that anomalous samples are accurately identified. A new weight function is introduced to control the proportion of losses in the encoding reconstruction and adversarial phases to achieve better results. An anomaly detection model is proposed to achieve superior performance against prior state-of-the-art approaches.

Data crawling in e-commerce for market research often come with the risk of poor authenticity due to modification attacks. The purpose of this paper is to propose a novel data authentication model for such systems.

The data modification problem requires careful examinations in which the data are re-collected to verify their reliability by overlapping the two datasets. This approach is to use different anomaly detection techniques to determine which data are potential for frauds and to be re-collected. The paper also proposes a data selection model using their weights of importance in addition to anomaly detection. The target is to significantly reduce the amount of data in need of verification, but still guarantee that they achieve their high authenticity. Empirical experiments are conducted with real-world datasets to evaluate the efficiency of the proposed scheme.

The authors examine several techniques for detecting anomalies in the data of users and products, which give the accuracy of 80 per cent approximately. The integration with the weight selection model is also proved to be able to detect more than 80 per cent of the existing fraudulent ones while being careful not to accidentally include ones which are not, especially when the proportion of frauds is high.

With the rapid development of e-commerce fields, fraud detection on their data, as well as in Web crawling systems is new and necessary for research. This paper contributes a novel approach in crawling systems data authentication problem which has not been studied much.

The purpose of this paper is to address the problem of profiling human behaviour patterns captured in surveillance videos for the application of online normal behaviour recognition and anomaly detection.

A novel framework is developed for automatic behaviour profiling and online anomaly detection without any manual labeling of the training dataset.

Experimental results demonstrate the effectiveness and robustness of the authors' approach using noisy and sparse datasets collected from one real surveillance scenario.

To discover the topics, co‐clustering topic model not only captures the correlation between words, but also models the correlations between topics. The major difference between the conventional co‐clustering algorithms and the proposed CCMT is that CCMT shows a major improvement in terms of recall, i.e. interpretability.

The discrete Fourier transformation (DFT) has been proven to be a successful method for determining whether a discrete time series is seasonal and, if so, for detecting the period. This paper deals exclusively with rare data, in which instances occur periodically at a low frequency.

Data based on real-world situations is simulated for analysis.

Cycle number detection is done with spectral analysis, period detection is completed using DFT coefficients and signal shifts in the time domain are found using the convolution theorem. Additionally, a new method for detecting anomalies in binary, rare data is presented: the sum of distances. Using this method, expected events which have not occurred and unexpected events which have occurred at various sampling frequencies can be detected. Anomalies which are not considered outliers to be found.

Aliasing can contribute to extra frequencies which point to extra periods in the time domain. This can be reduced or removed with techniques such as windowing. In future work, this will be explored.

Applications include determining seasonality and thus investigating the underlying causes of hard drive failure, power outages and other undesired events. This work will also lend itself well to finding patterns among missing desired events, such as a scheduled hard drive backup or an employee's regular login to a server.

This paper has shown how seasonality and anomalies are successfully detected in seasonal, discrete, rare and binary data. Previously, the DFT has only been used for non-rare data.