Chapter 7 Data model recommendations for real-time machine learning applications: a suggestive approach
-
Mehul Mahrishi
Abstract
Machine learning (ML) applications have received much coverage in today’s marketplace. From automated business strategies to educational canvases to sports analytic, these systems are included everywhere. There are a bunch of ML systems that have made life easy for company administration. These applications include market segmentation, optimize pricing, suggest treatment to the patients and job recommendations. Apart from this, ML has automated churn prediction, text analysis and summarization. There are many applications that ML has simplified in terms of understanding and feasibility. ML has influenced the implementation differently but it has also changed storytelling through visualization tools. Now we live in the era of prescriptive analytics, and ML has helped develop such applications. This chapter explores the impact of ML in business development, application development through various models and practicability. One particular model may fit well for an application but it may not be suitable for other applications, and this certainly depends on the dataset and what we want to predict. This chapter attempts to clarify many of the ML models and their particular implementations. Various researchers have indicated that a particular ML paradigm performs well for a specific program. This chapter explains the ML models and their respective applications, that is, where a particular model fits in a much better way compared to others. This chapter claims that ML makes it possible to improve the reasoning process by using inductive, abductive, neural networks and genetic algorithms.
Abstract
Machine learning (ML) applications have received much coverage in today’s marketplace. From automated business strategies to educational canvases to sports analytic, these systems are included everywhere. There are a bunch of ML systems that have made life easy for company administration. These applications include market segmentation, optimize pricing, suggest treatment to the patients and job recommendations. Apart from this, ML has automated churn prediction, text analysis and summarization. There are many applications that ML has simplified in terms of understanding and feasibility. ML has influenced the implementation differently but it has also changed storytelling through visualization tools. Now we live in the era of prescriptive analytics, and ML has helped develop such applications. This chapter explores the impact of ML in business development, application development through various models and practicability. One particular model may fit well for an application but it may not be suitable for other applications, and this certainly depends on the dataset and what we want to predict. This chapter attempts to clarify many of the ML models and their particular implementations. Various researchers have indicated that a particular ML paradigm performs well for a specific program. This chapter explains the ML models and their respective applications, that is, where a particular model fits in a much better way compared to others. This chapter claims that ML makes it possible to improve the reasoning process by using inductive, abductive, neural networks and genetic algorithms.
Kapitel in diesem Buch
- Frontmatter I
- Preface V
- Contents VII
- About editors IX
- List of contributors XI
- Chapter 1. A framework for applying artificial intelligence (AI) with Internet of nanothings (IoNT) 1
- Chapter 2 Opportunities and challenges in transforming higher education through machine learning 17
- Chapter 3 Efficient renewable energy integration: a pertinent problem and advanced time series data analytics solution 31
- Chapter 4 A comprehensive review on the application of machine learning techniques for analyzing the smart meter data 53
- Chapter 5 Application of machine learning algorithms for facial expression analysis 77
- Chapter 6 Prediction of quality analysis for crop based on machine learning model 97
- Chapter 7 Data model recommendations for real-time machine learning applications: a suggestive approach 115
- Chapter 8 Machine learning for sustainable agriculture 129
- Chapter 9 Application of machine learning in SLAM algorithms 147
- Chapter 10 Machine learning for weather forecasting 161
- Chapter 11 Applications of conventional machine learning and deep learning for automation of diagnosis: case study 175
- Index 199
Kapitel in diesem Buch
- Frontmatter I
- Preface V
- Contents VII
- About editors IX
- List of contributors XI
- Chapter 1. A framework for applying artificial intelligence (AI) with Internet of nanothings (IoNT) 1
- Chapter 2 Opportunities and challenges in transforming higher education through machine learning 17
- Chapter 3 Efficient renewable energy integration: a pertinent problem and advanced time series data analytics solution 31
- Chapter 4 A comprehensive review on the application of machine learning techniques for analyzing the smart meter data 53
- Chapter 5 Application of machine learning algorithms for facial expression analysis 77
- Chapter 6 Prediction of quality analysis for crop based on machine learning model 97
- Chapter 7 Data model recommendations for real-time machine learning applications: a suggestive approach 115
- Chapter 8 Machine learning for sustainable agriculture 129
- Chapter 9 Application of machine learning in SLAM algorithms 147
- Chapter 10 Machine learning for weather forecasting 161
- Chapter 11 Applications of conventional machine learning and deep learning for automation of diagnosis: case study 175
- Index 199
