Search results
1 – 10 of 460Qun Cao, Yuanqing Xia, Zhongqi Sun and Li Dai
This paper aims to design an algorithm which is used to deal with non-linear discrete systems with constraints under the lower computation burden. As a result, we solve the…
Abstract
Purpose
This paper aims to design an algorithm which is used to deal with non-linear discrete systems with constraints under the lower computation burden. As a result, we solve the non-holonomic vehicle tracking problem with the lower computational load and the convergence performance.
Design/methodology/approach
A fusion event-triggered model predictive control version is developed in this paper. The authors designed a shrinking prediction strategy.
Findings
The fusion event-triggered model predictive control scheme combines the strong points of event triggered and self-triggered methods. As the practical state approaches the terminal set, the computational complexity of optimal control problem (OCP) decreases.
Originality/value
The proposed strategy has proven to stabilize the system and also guarantee a reproducible solution for the OCP. Also, it is proved to be effected by the performance of the simulation results.
Details
Keywords
Timothy Webb, Zvi Schwartz, Zheng Xiang and Mehmet Altin
The pace of booking is a critical element in the accuracy of revenue management (RM) systems. Anecdotal evidence suggests that booking windows exhibit persistent shifts due to a…
Abstract
Purpose
The pace of booking is a critical element in the accuracy of revenue management (RM) systems. Anecdotal evidence suggests that booking windows exhibit persistent shifts due to a variety of macro and micro factors. The article outlines several causes and tests the impact of the shifts on forecasting accuracy.
Design/methodology/approach
A novel methodological approach is utilized to empirically shift hotel reservation windows into smaller increments. Forecasts are then estimated and tested on the incremental shifts with popular RM techniques characteristic of advance booking data. A random effects model assesses the impact of the shifts on forecast accuracy.
Findings
The results show that shifts in booking behavior can cause the accuracy of forecasting models to deteriorate. The findings stress the importance of considering these shifts in model estimation and evaluation.
Practical implications
The results demonstrate that changes in booking behavior can be detrimental to the accuracy of RM forecasting algorithms. It is recommended that revenue managers monitor booking window shifts when forecasting with advanced booking data.
Originality/value
This study is the first to systematically assess the impact of booking window shifts on forecasting accuracy. The demonstrated approach can be implemented in future research to assess model accuracy as booking behavior changes.
Details
Keywords
Hu Luo, Haobin Ruan and Dawei Tu
The purpose of this paper is to propose a whole set of methods for underwater target detection, because most underwater objects have small samples, low quality underwater images…
Abstract
Purpose
The purpose of this paper is to propose a whole set of methods for underwater target detection, because most underwater objects have small samples, low quality underwater images problems such as detail loss, low contrast and color distortion, and verify the feasibility of the proposed methods through experiments.
Design/methodology/approach
The improved RGHS algorithm to enhance the original underwater target image is proposed, and then the YOLOv4 deep learning network for underwater small sample targets detection is improved based on the combination of traditional data expansion method and Mosaic algorithm, expanding the feature extraction capability with SPP (Spatial Pyramid Pooling) module after each feature extraction layer to extract richer feature information.
Findings
The experimental results, using the official dataset, reveal a 3.5% increase in average detection accuracy for three types of underwater biological targets compared to the traditional YOLOv4 algorithm. In underwater robot application testing, the proposed method achieves an impressive 94.73% average detection accuracy for the three types of underwater biological targets.
Originality/value
Underwater target detection is an important task for underwater robot application. However, most underwater targets have the characteristics of small samples, and the detection of small sample targets is a comprehensive problem because it is affected by the quality of underwater images. This paper provides a whole set of methods to solve the problems, which is of great significance to the application of underwater robot.
Details
Keywords
Adrian Gepp, Martina K. Linnenluecke, Terrence J. O’Neill and Tom Smith
This paper analyses the use of big data techniques in auditing, and finds that the practice is not as widespread as it is in other related fields. We first introduce contemporary…
Abstract
This paper analyses the use of big data techniques in auditing, and finds that the practice is not as widespread as it is in other related fields. We first introduce contemporary big data techniques to promote understanding of their potential application. Next, we review existing research on big data in accounting and finance. In addition to auditing, our analysis shows that existing research extends across three other genealogies: financial distress modelling, financial fraud modelling, and stock market prediction and quantitative modelling. Auditing is lagging behind the other research streams in the use of valuable big data techniques. A possible explanation is that auditors are reluctant to use techniques that are far ahead of those adopted by their clients, but we refute this argument. We call for more research and a greater alignment to practice. We also outline future opportunities for auditing in the context of real-time information and in collaborative platforms and peer-to-peer marketplaces.
Details
Keywords
The main purpose of this study is to forecast inflation rates in the case of the Turkish economy with shrinkage methods of machine learning algorithms.
Abstract
Purpose
The main purpose of this study is to forecast inflation rates in the case of the Turkish economy with shrinkage methods of machine learning algorithms.
Design/methodology/approach
This paper compares the predictive ability of a set of machine learning techniques (ridge, lasso, ada lasso and elastic net) and a group of benchmark specifications (autoregressive integrated moving average (ARIMA) and multivariate vector autoregression (VAR) models) on the extensive dataset.
Findings
Results suggest that shrinkage methods perform better for variable selection. It is also seen that lasso and elastic net algorithms outperform conventional econometric methods in the case of Turkish inflation. These algorithms choose the energy production variables, construction-sector measure, reel effective exchange rate and money market indicators as the most relevant variables for inflation forecasting.
Originality/value
Turkish economy that is a typical emerging country has experienced two digit and high volatile inflation regime starting with the year 2017. This study contributes to the literature by introducing the machine learning techniques to forecast inflation in the Turkish economy. The study also compares the relative performance of machine learning techniques and different conventional methods to predict inflation in the Turkish economy and provide the empirical methodology offering the best predictive performance among their counterparts.
Details
Keywords
Pratheek Suresh and Balaji Chakravarthy
As data centres grow in size and complexity, traditional air-cooling methods are becoming less effective and more expensive. Immersion cooling, where servers are submerged in a…
Abstract
Purpose
As data centres grow in size and complexity, traditional air-cooling methods are becoming less effective and more expensive. Immersion cooling, where servers are submerged in a dielectric fluid, has emerged as a promising alternative. Ensuring reliable operations in data centre applications requires the development of an effective control framework for immersion cooling systems, which necessitates the prediction of server temperature. While deep learning-based temperature prediction models have shown effectiveness, further enhancement is needed to improve their prediction accuracy. This study aims to develop a temperature prediction model using Long Short-Term Memory (LSTM) Networks based on recursive encoder-decoder architecture.
Design/methodology/approach
This paper explores the use of deep learning algorithms to predict the temperature of a heater in a two-phase immersion-cooled system using NOVEC 7100. The performance of recursive-long short-term memory-encoder-decoder (R-LSTM-ED), recursive-convolutional neural network-LSTM (R-CNN-LSTM) and R-LSTM approaches are compared using mean absolute error, root mean square error, mean absolute percentage error and coefficient of determination (R2) as performance metrics. The impact of window size, sampling period and noise within training data on the performance of the model is investigated.
Findings
The R-LSTM-ED consistently outperforms the R-LSTM model by 6%, 15.8% and 12.5%, and R-CNN-LSTM model by 4%, 11% and 12.3% in all forecast ranges of 10, 30 and 60 s, respectively, averaged across all the workloads considered in the study. The optimum sampling period based on the study is found to be 2 s and the window size to be 60 s. The performance of the model deteriorates significantly as the noise level reaches 10%.
Research limitations/implications
The proposed models are currently trained on data collected from an experimental setup simulating data centre loads. Future research should seek to extend the applicability of the models by incorporating time series data from immersion-cooled servers.
Originality/value
The proposed multivariate-recursive-prediction models are trained and tested by using real Data Centre workload traces applied to the immersion-cooled system developed in the laboratory.
Details
Keywords
Forecasts from dynamic factor models potentially benefit from refining the data set by eliminating uninformative series. This paper proposes to use prediction weights as provided…
Abstract
Forecasts from dynamic factor models potentially benefit from refining the data set by eliminating uninformative series. This paper proposes to use prediction weights as provided by the factor model itself for this purpose. Monte Carlo simulations and an empirical application to short-term forecasts of euro area, German, and French GDP growth from unbalanced monthly data suggest that both prediction weights and least angle regressions result in improved nowcasts. Overall, prediction weights provide yet more robust results.
Details
Keywords
Prajwal Eachempati and Praveen Ranjan Srivastava
This study aims to develop two sentiment indices sourced from news stories and corporate disclosures of the firms in the National Stock Exchange NIFTY 50 Index by extracting…
Abstract
Purpose
This study aims to develop two sentiment indices sourced from news stories and corporate disclosures of the firms in the National Stock Exchange NIFTY 50 Index by extracting sentiment polarity. Subsequently, the two indices would be compared for the predictive accuracy of the stock market and stock returns during the post-digitization period 2011–2018. Based on the findings this paper suggests various options for financial strategy.
Design/methodology/approach
The news- and disclosure-based sentiment indices are developed using sentiment polarity extracted from qualitative content from news and corporate disclosures, respectively, using qualitative analysis tool “N-Vivo.” The indices developed are compared for stock market predictability using quantitative regression techniques. Thus, the study is conducted using both qualitative data and tools and quantitative techniques.
Findings
This study shows that the investor is more magnetized to news than towards corporate disclosures though disclosures contain both qualitative as well as quantitative information on the fundamentals of a firm. This study is extended to sectoral indices, and the results show that specific sectoral news impacts sectoral indices intensely over market news. It is found that the market discounts information in disclosures prior to its release. As disclosures in quarterly statements are delayed information input, firms can use voluntary disclosures to reduce the communication gap with investors by using the internet. Managers would do so only when the stock price is undervalued and tend to ignore the market and the shareholder in other cases. Otherwise, disclosure sentiment attracts only long horizon traders.
Practical implications
Finance managers need to improve disclosure dependence on investors by innovative disclosure methodologies irrespective of the ruling market price. In this context, future studies on investor sentiment would be interesting as they need to capture man–machine interactions reflected in market sentiment showing the interplay of human biases with machine-driven decisions. The findings would be useful in developing the financial strategy for protecting firm value.
Originality/value
This study is unique in providing a comparative analysis of sentiment extracted from news and corporate disclosures for explaining the stock market direction and stock returns and contributes to the behavioral finance literature.
Details
Keywords
Andrew B. Martinez, Jennifer L. Castle and David F. Hendry
We investigate whether smooth robust methods for forecasting can help mitigate pronounced and persistent failure across multiple forecast horizons. We demonstrate that naive…
Abstract
We investigate whether smooth robust methods for forecasting can help mitigate pronounced and persistent failure across multiple forecast horizons. We demonstrate that naive predictors are interpretable as local estimators of the long-run relationship with the advantage of adapting quickly after a break, but at a cost of additional forecast error variance. Smoothing over naive estimates helps retain these advantages while reducing the costs, especially for longer forecast horizons. We derive the performance of these predictors after a location shift, and confirm the results using simulations. We apply smooth methods to forecasts of UK productivity and US 10-year Treasury yields and show that they can dramatically reduce persistent forecast failure exhibited by forecasts from macroeconomic models and professional forecasters.
Details
Keywords
How should your company respond to the complex competitive challenge of declining demand? The model described here can increase your prospects of success.