Results for “"Petr Hájek"”

Mohammad Zoynul Abedin, Mahmudul Hasan Moon, M. Kabir Hassan, Petr Hájek

This study proposes an ensemble deep learning approach that integrates Bagging Ridge (BR) regression with Bi-directional Long Short-Term Memory (Bi-LSTM) neural networks used as base regressors to become a Bi-LSTM BR approach. Bi-LSTM BR was used to predict the exchange rates of 21 currencies agains...

Mohammad Zoynul Abedin, Chi Guotai, Petr Hájek, Tong Zhang

Abstract In small business credit risk assessment, the default and nondefault classes are highly imbalanced. To overcome this problem, this study proposes an extended ensemble approach rooted in the weighted synthetic minority oversampling technique (WSMOTE), which is called WSMOTE-ensemble. The pro...

Md Shajalal, Petr Hájek, Mohammad Zoynul Abedin

Taking backorders on products is a common scenario in inventory and supply chain management systems. The ability to predict the likelihood of backorders can surely minimise a company's losses. Because the number of backorders is much lower than the number of orders that ship on time, applying a pred...

Petr Hájek, Mohammad Zoynul Abedin

Inventory backorder prediction is widely recognized as an important component of inventory models. However, backorder prediction is traditionally based on stochastic approximation, thus neglecting the substantial amount of useful information hidden in historical inventory data. To provide those inve...

Md. Iftekharul Alam Efat, Petr Hájek, Mohammad Zoynul Abedin, Rahat Uddin Azad et al.

Mohammad Zoynul Abedin, Guotai Chi, Mohammed Mohi Uddin, Md. Shahriare Satu et al.

This study proposes to address the economic significance of unpaid taxes by using an automatic system for predicting a tax default. Too little attention has been paid to tax default prediction in the past. Moreover, existing approaches tend to apply conventional statistical methods rather than advan...

Mohammad Zoynul Abedin, Petr Hájek, Taimur Sharif, Md. Shahriare Satu et al.

This study investigates customer behaviour and activity in the banking sector and uses various feature transformation techniques to convert the behavioural data into different data structures. Feature selection is then performed to generate feature subsets from the transformed datasets. Several clas...

Mahmudul Hasan, Mohammad Zoynul Abedin, Petr Hájek, Kristof Coussement et al.

Abstract To efficiently capture diverse fluctuation profiles in forecasting crude oil prices, we here propose to combine heterogenous predictors for forecasting the prices of crude oil. Specifically, a forecasting model is developed using blended ensemble learning that combines various machine learn...

Fahmida-E-Moula, Nusrat Afrin Shilpa, Preity Shaha, Petr Hájek et al.