For many decades, time-series forecasting has been applied to different problems by scientists and industries. Many models have been introduced for the purpose of forecasting. Statistical techniques have been applied to this task since many years ago, after which neural network algorithms were introduced. Today, hybrid techniques are gaining popularity, aiming to put together the advantages of these two approaches. These hybrid approaches can provide better forecasting, and at the same time, they can develop a more sophisticated set of visualization analytics for decision support. And recently, the application of cross-entropy, fuzzy logic, and attention mechanisms in hybrid forecasting makes the modeling performed by these advanced systems more capable of modeling complex and uncertain situations in financial markets as well as in the energy market domain. These techniques turn out to be effective in increasing the accuracy of forecasting and in decision-making processes, with growing importance in various applications, as noticed in our paper.