Название: Modeling and Advanced Techniques in Modern Economics
Автор: Cagdas Hakan Aladag, Nihan Potas
Издательство: World Scientific Publishing
Год: 2022
Страниц: 328
Язык: английский
Формат: pdf (true)
Размер: 15.8 MB

In the modern world, data is a vital asset for any organization, regardless of industry or size. The world is built upon data. However, data without knowledge is useless. The aim of this book, briefly, is to introduce new approaches that can be used to shape and forecast the future by combining the two disciplines of Statistics and Economics. Readers of Modeling and Advanced Techniques in Modern Economics can find valuable information from a diverse group of experts on topics such as finance, econometric models, stochastic financial models and machine learning, and application of models to financial and macroeconomic data.

In this day and age, data is a vital asset for any organization, regardless of industry or size. The world is built upon data. It is not only data but also having the right kind of knowledge is critically important today. In order to obtain the right kind of knowledge from data, the process of analyzing data is very crucial for individuals, organizations or governments. This is why the concept of Data Science is so popular today. Nowadays, many researchers and practitioners from various fields are studying advanced data analysis techniques. One of these fields is Economics. For example, time series analysis is very important for economics. Time series, which is a collection of data points collected at constant time intervals, is one of the most important data types. People have tried to forecast time series by different methods for a long time. Forecasting is so essential since the prediction of future events is a critical input for many types of planning decision-making processes, with real-world applications in all areas.

With the development of technology and algorithms, time series forecasting approaches are developing. Thus, it is possible to reach more accurate predictions of the future by using advanced forecasting approaches. In this manner, some chapters of this book are intended to be a valuable source of recent knowledge on advanced time series forecasting techniques. These chapters include applications of efficient, recent forecasting approaches. The readers can also find useful information on advanced time series forecasting techniques, such as artificial neural networks, deep learning, machine learning and chaotic time series. In addition to these time series applications, some chapters introduce some other recent data analysis methods such as fiducial method, a novel approach based on inverse Gaussian distribution and weighted superposition attraction–repulsion algorithm. An example of time series forecasting with Python code and results for LSTM are given.

Contents:

Smart Growth Developments of Europe Union Members by Europe 2020 Strategies
Spatial Regression Model Specification and Measurement Errors
Determining Harmonic Fluctuations in Food Inflation
Nonlinear and Chaotic Time Series Analysis
A Fiducial-based Test for the Equality of Location Parameters
Understanding the Effects of Green Swan Events on Financial Stability
Forecasting the BIST 100 Index with Support Vector Machines
Multiple Objective Optimization with Weighted Superposition Attraction–Repulsion Algorithm (moWSAR) Algorithm
Time Series Modeling with Deep Neural Networks
An Extension of the Inverse Gaussian Distribution
Clustering Eurozone Countries According to Employee Contributions
Criteria for Best Architecture Selection in Artificial Neural Networks

Readership: The book is primarily aimed at academics, researchers, and postgraduate students interested in new economic perspectives with modeling and advanced techniques. A secondary audience involves practitioners and policymakers from diverse related fields.