Takeover prediction using forecast combinations

This paper is the first study on the intra-industry effects of proxy contests. Using a sample of proxy contests from January 1988 through December 2008, we identify a striking cross-sectional difference in market reaction to the target companies. As much as 61% of the target firms have significant positive cumulative abnormal return (CARs) in the period (‒10, +10) around the announcement day, while 39% of the target firms have the negative CARs in the same event window. Moreover, we find that the stock market reaction to the target firms’ competitors is primarily driven by the target-related factors when the market reacts favorably to a proxy contest. In contrast, the stock market reaction to the competitors is mainly affected by the competitor-related factors when the market reacts unfavorably to the proxy contest. We further reveal that competitors experience a significant negative abnormal stock return when the target firms receive negative market reactions, while competitors have no significant abnormal return when the target firms receive a positive market reaction. Our findings enrich the corporate governance research by showing the impact of the target firms’ corporate governance change on the firms’ competitors.

The Long-Run Performance of REIT IPOs

In this study, a new hybrid forecasting method is proposed. The proposed method is called autoregressive adaptive network fuzzy inference system (AR---ANFIS). AR---ANFIS can be shown in a network structure. The architecture of the network has two parts. The first part is an ANFIS structure and the second part is a linear AR model structure. In the literature, AR models and ANFIS are widely used in time series forecasting. Linear AR models are used according to model-based strategy. A nonlinear model is employed by using ANFIS. Moreover, ANFIS is a kind of data-based modeling system like artificial neural network. In this study, a linear and nonlinear forecasting model is proposed by creating a hybrid method of AR and ANFIS. The new method has advantages of data-based and model-based approaches. AR---ANFIS is trained by using particle swarm optimization, and fuzzification is done by using fuzzy C-Means method. AR---ANFIS method is examined on some real-life time series data, and it is compared with the other time series forecasting methods. As a consequence of applications, it is shown that the proposed method can produce accurate forecasts.

In prediction of dam safety monitoring, single models such as mathematical model and neural network model are established according to different modeling mechanism. The effective combination of these single models can make full use of all useful information and improve the fitting and forecasting precision. The most commonly used combination method is weighted arithmetic averaging combination forecasting method, in which each single forecasting model is endowed with the same weighted averaging coefficient at various moments. But in fact, each single forecasting model has different performance at various moments, namely, exhibiting higher prediction accuracy at one moment and lower prediction accuracy at another moment. Thus, this combination forecasting method is not absolutely reasonable. Therefore, the concept of induced ordered weighted averaging (IOWA) operator is introduced here, and then a new dam safety monitoring combination forecasting model based on IOWA operator is put forward. In this combination model, each single forecasting model is endowed with weights orderly according to its prediction accuracy at each moment. Case study shows that the proposed combination forecasting model is superior to various single forecasting models. It has high fitting and forecasting accuracy and is applicable to prediction of various dam safety monitoring indexes.

Different forecasting methods can lead to very different results in power system load forecast. In order to improve forecasting accuracy, combined forecasting methods have been introduced in solving the engineering forecasting problems. In this paper, the conception of soft method is first presented in power system load forecast. The computing and analyzing methods in soft science such as decision-making analyses have been introduced to solve load forecast that are unstructured problems of multi-factors. The combined forecasting problem is treated as multi-hierarchies and multi-factors evaluation by composing qualitative analyses and quantitative calculation. In addition, the experiences and judgments of experts will be collected to implement judgment matrices in group decisionmaking. The soft method based on improved analytic hierarchy process (AHP) is proposed to carry out long-middle term load combined forecast in this paper. A hierarchy structure has been established by analyzing various factors that affect the load forecast. It is the key to determining the combined weight coefficients in the optimal combined forecasting method. Fuzzy complementary judgment matrixes of pairwise comparison will be formed by the expert in each hierarchy and be converted to a fuzzy consistent matrix. The eigenvector can be calculated using its general formula and be regarded as weight coefficient in combined forecasting. The combined forecast methods based on the improved AHP is of clear hierarchy structure, sufficient judgment information and simple calculation formula. The forecasting examples show that this method is practical, convenient and accurate.

Conventional membership inference attacks usually require a large number of queries of the target model when training shadow models, and this task becomes extremely difficult when the number of queries is limited. Aiming at the problem of insufficient training data for shadow models due to the limited number of queries, we propose a membership inference attack method based on generative adversarial networks (GAN). First, we use generative adversarial networks to augment the samples obtained by a small number of queries to expand the training data of the model; Secondly, we use the improved CNN to obtain shadow models that have a higher degree of fitting on different target model structures; Finally, we evaluate the accuracy of the proposed algorithm on XgBoost, Logistic, and neural network models using public datasets MNIST and CIFAR10 in a black-box setting, and the results show that our model has an average attack accuracy of 62% and 83%, respectively. It can be seen that, compared with the existing research methods, our model can obtain better attack effects under the condition of significantly reducing the number of queries, which shows the feasibility of our proposed method in membership inference attacks.

Logistic service providers are facing significant challenges in recent years due to intensified competition and ever-increasing customer expectations for cohesive high-standard services at low cost. To cope with these developments many companies aim for external growth to realize operational efficiencies and exploit productive opportunities of new markets and diversified services. Accordingly, 2015 has even become the most active year for mergers and acquisitions in logistic service industry. However, studies examining the post-merger performance effect and its determinants are scarce. Consequently, this paper takes up this issue by analysing a sample of 826 transaction announcements taken place between 1996 and 2015 and their performance effect in terms of short- and long-term abnormal shareholder returns. The results reveal, that although overall transactions exhibit significant positive abnormal returns, post-merger performance for the acquiring companies differs considerably according to the logistic services offered. In the short-term trucking, railway, 3PL and air cargo companies experience significant positive abnormal returns of about 0.6%–2.6%, while sea freight carriers realize only marginal effects and CEP companies do even not show any significant reaction. In the long-term, railway and 3PL companies realize a significant abnormal return of about 20%–24%, while trucking, sea freight and air cargo carriers do not exhibit significant returns and CEP companies do even experience significant losses of about −17%. Overall, diversifying transactions of established full-service providers outperform focus-increasing transactions of specialized operators.

Bioinformatic predictions of neuropeptides resulting from enzymatic cleavages of precursors enable a range of follow-up studies that are aided by accurate predictions. A comparative study of the performance of complementary cleavage prediction models has been undertaken. Binary logistic and artificial neural network (ANN) models were created using various strategies and trained and tested on bovine and rat precursors with experimental cleavage information. Multiple criteria were used to compare 4 logistic regression models with varying properties and 8 ANN with varying structures. All models had high specificity (>90%) and sensitivity ranged from 68% to 100%. ANN based on well-represented amino acid locations performed similarly or slightly worse than networks based on all amino acid locations. Logistic parameter estimates aided in the identification of amino acids associated with cleavage. No model was superior across data sets and thus, prediction of neuropeptides should rely on multiple model specifications and comprehensive training data sets.

This study examines the performance of acquisitions in the Real Estate Investment Trust (REIT) industry around the acquisition announcement and in the long-run. The results suggest that the acquiring REITs experience statistically significant negative abnormal returns while the target REITs earn statistically significant positive abnormal returns during the three-day period around the announcement. The long-run performance of the acquiring REITs is analyzed using size benchmark portfolios with the buy-and-hold, cumulative average and mean calendar time abnormal returns, as well as the Fama-French Three Factor Model. None of the other methods detect significant abnormal returns in the long-run with the exception of the buy-and-hold abnormal return. Further analysis shows that the long-run positive buy-and-hold abnormal return is consistent with an unexpected decline in cost of equity after acquisitions.

We examine the merger announcements of Canadian companies between 1994 and 2000 during an exceptional merger boom. Our results show that both target companies and the acquirer companies obtain significant positive abnormal returns at this time period. However, in the long run, we observe that abnormal returns diminish to become significant and negative for acquiring companies and diminish to be non-significant and positive for target companies. We find acquiring companies to have significantly higher risk that purchase private targets compared with public targets, despite non-significant differences in returns. Our large sample study updates and fills a void in Canadian merger studies during this important and recent time period in merger and acquisitions.

In recent years, syndicated loan had played an important role in corporate financing. This study focus on whether the announcement of syndicated loan could influence the stock price in Taiwan stock market. We analysis the TSEC & OTC listed companies which has acquired syndicated loan from 2000 to 2010. This mythology was event study and the observations which were collected from Taiwan Economic Journal Data Bank (TEJ) were separated into three subgroups: (1) the date of syndicated loan announcement on the Market Observation Post System, (2) the date of board of directors' meetings, (3) the date of syndicated loan announcement on newspapers. The empirical results found that only group 1 could obtain significant positive abnormal return on the event day which proves that the announcement of syndicated loan has announcement effect on stock price. The results of group 2 showed that there was significant negative abnormal return on t = -1, in contrast, there was significant negative abnormal return on t = 1. However, there wasn’t significant announcement effect on the event day. Finally, the results of group 3 explored that there wasn’t significant announcement effect on the event day.

ABSTRACTIn this research, an ARIMA-NARX (Autoregressive Integrated Moving Average-Nonlinear Auto-Regressive eXogenous) hybrid model is proposed to forecast daily Urban Water Consumption (UWC) for Tehran Metropolis. The linear and nonlinear component of the UWC was forecast by ARIMA as a linear forecasting model and the artificial neural network as a nonlinear forecasting model, respectively. An alternative hybrid model including sunshine hour in addition to the previous studies’ predictors (the minimum, maximum and average temperature, relative humidity and precipitation) was selected as the superior alternative model. Then, the performance of proposed model was compared with ARIMA and NARX models. The results showed that the hybrid model, which benefits from capability of both linear and nonlinear models, has a higher accuracy than the other two models in forecasting UWC. Therefore, the proposed hybrid model has better results in UWC forecasting and, as a consequence, better urban water reservoir management will be provided.

Forecasting of economic indicators with time series using one or another method or another but the only method leads to the situation that all the information contained in other forecasting methods is usually discarded. The information that is ignored may contain information that allows other features of the economic process to be assessed. Combining forecasts makes possible to take into account almost all the information contained in particular forecasts. In the article, we present the analysis of the application of the method of regression analysis, in particular, ridge regression for finding the weighting coefficients of the particular forecasts in the combined forecast. We compared the accuracy of prediction based on the ridge regression with other methods of combining predictions. The purpose of our research work was an analysis of the most common methods of combining forecasts — various modifications of Granger-Ramanathan methods and comparison with a new approach of combining forecasts based on the ridge regression for its use in practice. We used statistical methods of time series forecasting (the method of harmonic weights, adaptive exponential smoothing using a tracking signal, the method of simple exponential smoothing and the Box-Jenkins model), the method of constructing combined forecasts, as well as methods of regression analysis. As a result, we built the combined forecasts based on annual data for the period from 1950 to 2015 on the production in Russia of some products: steel, metallurgical coke, pulp, plywood, cement. We used the methods of Granger-Ramanathan (without restrictions and with restrictions on the sum of coefficients in partial predictions) and also the ∆-coefficients obtained by the ridge regression method. The forecasts constructed using the Granger-Ramanathan methods give the highest accuracy of the combined forecast. The method based on the ridge regression is less accurate, but better than the separate predictions. At the same time, the proposed method of calculating the weight coefficients on the basis of the ridge regression has a well- developed scheme of calculation and eliminates the negative weight coefficients in the combined forecast.

Learning What Makes Catalysts Good

1. In this study, neural network (NN) and response surface (RS) models were developed to investigate the response [average daily gain (ADG) and feed efficiency (FE)] of young broiler chickens to dietary protein and lysine. For this purpose, data on their responses to dietary protein and lysine were extracted from the literature and separate NN and RS models were constructed. 2. Comparison between the NN and RS models revealed higher accuracy of prediction with the NN models compared to the RS models. In terms of R 2 values, the NN models developed for both ADG (R 2 = 0.923) and FE (R 2 = 0.904) were far superior to the RS models (R 2 for ADG = 0.511; R 2 for FE = 0.67). This suggests that the NN models can serve as an alternative option to conventional regression approaches including use of RS models. 3. Optimisation of the NN models developed for response to protein and lysine showed that diets containing 220.7 (g/kg of diet) protein and 12.85 (g/kg of diet) lysine maximise ADG, whereas maximum FE is achieved with diets containing 241.3 and 13.12 (g/kg) protein and lysine, respectively. Based on the optimisation results, optimal dietary protein and lysine concentrations for maximum FE in broiler chickens during the starting period are higher than for ADG.