{"product_id":"machine-learning-for-time-series-forecasting-with-python-isbn-9781119682363","title":"Machine Learning for Time Series Forecasting with Python","description":"\u003cp\u003e\u003cb\u003eLearn how to apply the principles of machine learning to \u003c\/b\u003e\u003cb\u003etime series modeling with this indispensable resource\u003c\/b\u003e \u003c\/p\u003e \u003cp\u003e\u003ci\u003eMachine Learning for Time Series Forecasting with Python\u003c\/i\u003e is an incisive and straightforward examination of one of the most crucial elements of decision-making in finance, marketing, education, and healthcare: time series modeling.  \u003c\/p\u003e \u003cp\u003eDespite the centrality of time series forecasting, few business analysts are familiar with the power or utility of applying machine learning to time series modeling. Author Francesca Lazzeri, a distinguished machine learning scientist and economist, corrects that deficiency by providing readers with comprehensive and approachable explanation and treatment of the application of machine learning to time series forecasting. \u003c\/p\u003e \u003cp\u003eWritten for readers who have little to no experience in time series forecasting or machine learning, the book comprehensively covers all the topics necessary to: \u003c\/p\u003e \u003cul\u003e \u003cli\u003eUnderstand time series forecasting concepts, such as stationarity, horizon,  trend, and seasonality  \u003c\/li\u003e \u003cli\u003ePrepare time series data for modeling \u003c\/li\u003e \u003cli\u003eEvaluate time series forecasting models’ performance and accuracy \u003c\/li\u003e \u003cli\u003eUnderstand when to use neural networks instead of traditional time series models in time series forecasting \u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003e\u003ci\u003eMachine Learning for Time Series Forecasting with Python \u003c\/i\u003eis full real-world examples, resources and concrete strategies to help readers explore and transform data and develop usable, practical time series forecasts. \u003c\/p\u003e \u003cp\u003ePerfect for entry-level data scientists, business analysts, developers, and researchers, this book is an invaluable and indispensable guide to the fundamental and advanced concepts of machine learning applied to time series modeling. \u003c\/p\u003e \u003cp\u003e \u003c\/p\u003e \u003cp\u003e \u003c\/p\u003e \u003cp\u003eAcknowledgments vii\u003c\/p\u003e \u003cp\u003eIntroduction xv\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 Overview of Time Series Forecasting 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eFlavors of Machine Learning for Time Series Forecasting 3\u003c\/p\u003e \u003cp\u003eSupervised Learning for Time Series Forecasting 14\u003c\/p\u003e \u003cp\u003ePython for Time Series Forecasting 21\u003c\/p\u003e \u003cp\u003eExperimental Setup for Time Series Forecasting 24\u003c\/p\u003e \u003cp\u003eConclusion 26\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 How to Design an End-to-End Time Series Forecasting Solution on the Cloud 29\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTime Series Forecasting Template 31\u003c\/p\u003e \u003cp\u003eBusiness Understanding and Performance Metrics 33\u003c\/p\u003e \u003cp\u003eData Ingestion 36\u003c\/p\u003e \u003cp\u003eData Exploration and Understanding 39\u003c\/p\u003e \u003cp\u003eData Pre-processing and Feature Engineering 40\u003c\/p\u003e \u003cp\u003eModeling Building and Selection 42\u003c\/p\u003e \u003cp\u003eAn Overview of Demand Forecasting Modeling Techniques 44\u003c\/p\u003e \u003cp\u003eModel Evaluation 46\u003c\/p\u003e \u003cp\u003eModel Deployment 48\u003c\/p\u003e \u003cp\u003eForecasting Solution Acceptance 53\u003c\/p\u003e \u003cp\u003eUse Case: Demand Forecasting 54\u003c\/p\u003e \u003cp\u003eConclusion 58\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Time Series Data Preparation 61\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003ePython for Time Series Data 62\u003c\/p\u003e \u003cp\u003eCommon Data Preparation Operations for Time Series 65\u003c\/p\u003e \u003cp\u003eTime stamps vs. Periods 66\u003c\/p\u003e \u003cp\u003eConverting to Timestamps 69\u003c\/p\u003e \u003cp\u003eProviding a Format Argument 70\u003c\/p\u003e \u003cp\u003eIndexing 71\u003c\/p\u003e \u003cp\u003eTime\/Date Components 76\u003c\/p\u003e \u003cp\u003eFrequency Conversion 78\u003c\/p\u003e \u003cp\u003eTime Series Exploration and Understanding 79\u003c\/p\u003e \u003cp\u003eHow to Get Started with Time Series Data Analysis 79\u003c\/p\u003e \u003cp\u003eData Cleaning of Missing Values in the Time Series 84\u003c\/p\u003e \u003cp\u003eTime Series Data Normalization and Standardization 86\u003c\/p\u003e \u003cp\u003eTime Series Feature Engineering 89\u003c\/p\u003e \u003cp\u003eDate Time Features 90\u003c\/p\u003e \u003cp\u003eLag Features and Window Features 92\u003c\/p\u003e \u003cp\u003eRolling Window Statistics 95\u003c\/p\u003e \u003cp\u003eExpanding Window Statistics 97\u003c\/p\u003e \u003cp\u003eConclusion 98\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Introduction to Autoregressive and Automated Methods for Time Series Forecasting 101\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eAutoregression 102\u003c\/p\u003e \u003cp\u003eMoving Average 119\u003c\/p\u003e \u003cp\u003eAutoregressive Moving Average 120\u003c\/p\u003e \u003cp\u003eAutoregressive Integrated Moving Average 122\u003c\/p\u003e \u003cp\u003eAutomated Machine Learning 129\u003c\/p\u003e \u003cp\u003eConclusion 136\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Introduction to Neural Networks for Time Series Forecasting 137\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eReasons to Add Deep Learning to Your Time Series Toolkit 138\u003c\/p\u003e \u003cp\u003eDeep Learning Neural Networks Are Capable of Automatically Learning and Extracting Features from Raw and Imperfect Data 140\u003c\/p\u003e \u003cp\u003eDeep Learning Supports Multiple Inputs and Outputs 142\u003c\/p\u003e \u003cp\u003eRecurrent Neural Networks Are Good at Extracting Patterns from Input Data 143\u003c\/p\u003e \u003cp\u003eRecurrent Neural Networks for Time Series Forecasting 144\u003c\/p\u003e \u003cp\u003eRecurrent Neural Networks 145\u003c\/p\u003e \u003cp\u003eLong Short-Term Memory 147\u003c\/p\u003e \u003cp\u003eGated Recurrent Unit 148\u003c\/p\u003e \u003cp\u003eHow to Prepare Time Series Data for LSTMs and GRUs 150\u003c\/p\u003e \u003cp\u003eHow to Develop GRUs and LSTMs for Time Series Forecasting 154\u003c\/p\u003e \u003cp\u003eKeras 155\u003c\/p\u003e \u003cp\u003eTensorFlow 156\u003c\/p\u003e \u003cp\u003eUnivariate Models 156\u003c\/p\u003e \u003cp\u003eMultivariate Models 160\u003c\/p\u003e \u003cp\u003eConclusion 164\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Model Deployment for Time Series Forecasting 167\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eExperimental Set Up and Introduction to Azure Machine Learning SDK for Python 168\u003c\/p\u003e \u003cp\u003eWorkspace 169\u003c\/p\u003e \u003cp\u003eExperiment 169\u003c\/p\u003e \u003cp\u003eRun 169\u003c\/p\u003e \u003cp\u003eModel 170\u003c\/p\u003e \u003cp\u003eCompute Target, RunConfiguration, and ScriptRun Config 171\u003c\/p\u003e \u003cp\u003eImage and Webservice 172\u003c\/p\u003e \u003cp\u003eMachine Learning Model Deployment 173\u003c\/p\u003e \u003cp\u003eHow to Select the Right Tools to Succeed with Model Deployment 175\u003c\/p\u003e \u003cp\u003eSolution Architecture for Time Series Forecasting with Deployment Examples 177\u003c\/p\u003e \u003cp\u003eTrain and Deploy an ARIMA Model 179\u003c\/p\u003e \u003cp\u003eConfigure the Workspace 182\u003c\/p\u003e \u003cp\u003eCreate an Experiment 183\u003c\/p\u003e \u003cp\u003eCreate or Attach a Compute Cluster 184\u003c\/p\u003e \u003cp\u003eUpload the Data to Azure 184\u003c\/p\u003e \u003cp\u003eCreate an Estimator 188\u003c\/p\u003e \u003cp\u003eSubmit the Job to the Remote Cluster 188\u003c\/p\u003e \u003cp\u003eRegister the Model 189\u003c\/p\u003e \u003cp\u003eDeployment 189\u003c\/p\u003e \u003cp\u003eDefine Your Entry Script and Dependencies 190\u003c\/p\u003e \u003cp\u003eAutomatic Schema Generation 191\u003c\/p\u003e \u003cp\u003eConclusion 196\u003c\/p\u003e \u003cp\u003eReferences 197\u003c\/p\u003e \u003cp\u003eIndex 199\u003c\/p\u003e   \u003cp\u003e\u003cb\u003eFRANCESCA LAZZERI\u003c\/b\u003e is an accomplished economist who works with machine learning, artificial intelligence, and applied econometrics. She works at Microsoft as a data scientist and machine learning scientist to develop a portfolio of machine learning services. She is a sought-after speaker and has given popular talks at AI conferences and academic seminars at Berkeley, Harvard, and MIT.\u003c\/p\u003e  \u003cp\u003e\u003cb\u003eDiscover hands-on techniques to build robust business forecasting models\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e\u003ci\u003eMachine Learning for Time Series Forecasting with Python\u003c\/i\u003e shows readers how to implement accurate and practical time series forecasting models using the Python programming language. Accomplished economist, data scientist, and author Francesca Lazzeri walks you through the foundational and advanced steps necessary to create successful forecasting applications. \u003c\/p\u003e\u003cp\u003eHighly useful in industries as varied as finance, education, and health care, time series forecasting plays a major role in decision-making for businesspeople of all sorts. This book demystifies the technique, providing readers with little or no time series or machine learning experience the fundamental tools required to create and evaluate time series models. \u003c\/p\u003e\u003cp\u003e\u003ci\u003eMachine Learning for Time Series Forecasting with Python\u003c\/i\u003e uses popular and common Python tools and libraries to accelerate your ability to solve complex and important business forecasting problems. You'll learn how to clean and ingest data, design end-to-end time series forecasting solutions, understand some classical methods for time series forecasting, incorporate neural networks into your forecasting models, and how to deploy your time series forecasting models for use in the real world. \u003c\/p\u003e\u003cp\u003ePerfect for business analysts with two to three years of experience, developers, and data scientists, this book also belongs on the shelves of researchers familiar with time series forecast theoretical concepts but lacking in hands-on experience. \u003c\/p\u003e\u003cp\u003eWritten in a practical and accessible style, \u003ci\u003eMachine Learning for Time Series Forecasting with Python\u003c\/i\u003e teaches you: \u003c\/p\u003e\u003cul\u003e \u003cli\u003eTime series forecasting concepts like horizon, frequency, trend, and seasonality\u003c\/li\u003e \u003cli\u003eHow to evaluate the performance and accuracy of time series forecasting models\u003c\/li\u003e \u003cli\u003eWhen to use neural networks instead of traditional time series models in a forecasting application\u003c\/li\u003e \u003cli\u003eHow to explore time series data, transform it, and use it to develop time series forecasting models\u003c\/li\u003e \u003cli\u003eHow to use popular Python tools and packages like Jupyter notebooks, Scikit-learn, Keras, and TensorFlow\u003c\/li\u003e \u003c\/ul\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47989548744933,"sku":"NP9781119682363","price":60.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781119682363.jpg?v=1761784553","url":"https:\/\/k12savings.com\/es\/products\/machine-learning-for-time-series-forecasting-with-python-isbn-9781119682363","provider":"K12savings","version":"1.0","type":"link"}