Econometrics and Data Science: Apply Data Science Techniques to Model Complex Problems and Implement Solutions for Economic Problems

This book provides an introduction to machine learning approaches in macroeconomic research, covering topics such as covariance analysis, correlation analysis, cross-validation, hyperparameter optimization, regression analysis, residual analysis, and more. It also discusses unsupervised machine learning techniques like principal component analysis and cluster analysis and explores key deep learning concepts and neural networks. The book demonstrates how machine learning can be applied to model complex economic problems and discusses the practical implications of a machine learning approach in econometrics.

Format: Paperback / softback
Length: 228 pages
Publication date: 27 October 2021
Publisher: APress

This comprehensive book delves into the realm of macroeconomic research, seamlessly merging economics and data science. Author Tshepo Chris Nokeri kickstarts the journey by introducing key concepts such as covariance analysis, correlation analysis, cross-validation, hyperparameter optimization, regression analysis, and residual analysis. He also presents an innovative approach to tackling multi-collinearity, a common challenge in economic modeling. Nokeri then dismantles a widely recognized time series model, the additive model, and unveils a technique for binarizing economic features for classification analysis using logistic regression. He further incorporates the Hidden Markov Model, a powerful tool for uncovering hidden patterns and economic growth trends. The author showcases unsupervised machine learning techniques like principal component analysis and cluster analysis, enabling the identification of hidden structures and patterns within economic data. Additionally, he delves into key deep learning concepts, including structuring artificial neural networks and training them for optimal performance. The book employs the Monte Carlo simulation technique to explore the impact of monetary purchasing power on an economy. Furthermore, it considers the Structural Equation Model (SEM), a powerful tool for integrating correlation analysis, factor analysis, multivariate analysis, causal analysis, and path analysis. By the end of this book, readers will have a deep understanding of the interplay between econometrics and data science. They will acquire the skills to apply machine learning approaches to model complex economic problems and extend their knowledge beyond the scope of this book. Readers will also gain practical insights into the implications of machine learning in econometrics, enabling them to address pressing economic challenges with confidence.

Weight: 482g
Dimension: 177 x 254 x 18 (mm)
ISBN-13: 9781484274330
Edition number: 1st ed.