Specifically addresses recommendation engines from a mathematically rigorous viewpoint
Discusses a control-theoretic framework for recommendation engines
Provides applications to a number of areas within engineering and computer science
Describing novel mathematical concepts for recommendation engines, Realtime Data Mining: Self-Learning Techniques for Recommendation Engines features a sound mathematical framework unifying approaches based on control and learning theories, tensor factorization, and hierarchical methods. Furthermore, it presents promising results of numerous experiments on real-world data. The area of realtime data mining is currently developing at an exceptionally dynamic pace, and realtime data mining systems are the counterpart of today's "classic” data mining systems. Whereas the latter learn from historical data and then use it to deduce necessary actions, realtime analytics systems learn and act continuously and autonomously. In the vanguard of these new analytics systems are recommendation engines. They are principally found on the Internet, where all information is available in realtime and an immediate feedback is guaranteed.
This monograph appeals to computer scientists and specialists in machine learning, especially from the area of recommender systems, because it conveys a new way of realtime thinking by considering recommendation tasks as control-theoretic problems. Realtime Data Mining: Self-Learning Techniques for Recommendation Engines will also interest application-oriented mathematicians because it consistently combines some of the most promising mathematical areas, namely control theory, multilevel approximation, and tensor factorization.
1 Brave New Realtime World – Introduction.- 2 Strange Recommendations? – On The Weaknesses Of Current Recommendation Engines.- 3 Changing Not Just Analyzing – Control Theory And Reinforcement Learning.- 4 Recommendations As A Game – Reinforcement Learning For Recommendation Engines.- 5 How Engines Learn To Generate Recommendations – Adaptive Learning Algorithms.- 6 Up The Down Staircase – Hierarchical Reinforcement Learning.- 7 Breaking Dimensions – Adaptive Scoring With Sparse Grids.- 8 Decomposition In Transition - Adaptive Matrix Factorization.- 9 Decomposition In Transition Ii - Adaptive Tensor Factorization.- 10 The Big Picture – Towards A Synthesis Of Rl And Adaptive Tensor Factorization.- 11 What Cannot Be Measured Cannot Be Controlled - Gauging Success With A/B Tests.- 12 Building A Recommendation Engine – The Xelopes Library.- 13 Last Words – Conclusion.- References.- Summary Of Notation.
Describing novel mathematical concepts for recommendation engines, Realtime Data Mining: Self-Learning Techniques for Recommendation Engines features a sound mathematical framework unifying approaches based on control and learning theories, tensor factorization, and hierarchical methods. Furthermore, it presents promising results of numerous experiments on real-world data. The area of realtime data mining is currently developing at an exceptionally dynamic pace, and realtime data mining systems are the counterpart of today's "classic" data mining systems. Whereas the latter learn from historical data and then use it to deduce necessary actions, realtime analytics systems learn and act continuously and autonomously. In the vanguard of these new analytics systems are recommendation engines. They are principally found on the Internet, where all information is available in realtime and an immediate feedback is guaranteed.
This monograph appeals to computer scientists and specialists in machine learning, especially from the area of recommender systems, because it conveys a new way of realtime thinking by considering recommendation tasks as control-theoretic problems. Realtime Data Mining: Self-Learning Techniques for Recommendation Engines will also interest application-oriented mathematicians because it consistently combines some of the most promising mathematical areas, namely control theory, multilevel approximation, and tensor factorization.
1 Brave New Realtime World - Introduction.- 2 Strange Recommendations? - On The Weaknesses Of Current Recommendation Engines.- 3 Changing Not Just Analyzing - Control Theory And Reinforcement Learning.- 4 Recommendations As A Game - Reinforcement Learning For Recommendation Engines.- 5 How Engines Learn To Generate Recommendations - Adaptive Learning Algorithms.- 6 Up The Down Staircase - Hierarchical Reinforcement Learning.- 7 Breaking Dimensions - Adaptive Scoring With Sparse Grids.- 8 Decomposition In Transition - Adaptive Matrix Factorization.- 9 Decomposition In Transition Ii - Adaptive Tensor Factorization.- 10 The Big Picture - Towards A Synthesis Of Rl And Adaptive Tensor Factorization.- 11 What Cannot Be Measured Cannot Be Controlled - Gauging Success With A/B Tests.- 12 Building A Recommendation Engine - The Xelopes Library.- 13 Last Words - Conclusion.- References.- Summary Of Notation.
Inhaltsverzeichnis
1 Brave New Realtime World - Introduction.- 2 Strange Recommendations? - On The Weaknesses Of Current Recommendation Engines.- 3 Changing Not Just Analyzing - Control Theory And Reinforcement Learning.- 4 Recommendations As A Game - Reinforcement Learning For Recommendation Engines.- 5 How Engines Learn To Generate Recommendations - Adaptive Learning Algorithms.- 6 Up The Down Staircase - Hierarchical Reinforcement Learning.- 7 Breaking Dimensions - Adaptive Scoring With Sparse Grids.- 8 Decomposition In Transition - Adaptive Matrix Factorization.- 9 Decomposition In Transition Ii - Adaptive Tensor Factorization.- 10 The Big Picture - Towards A Synthesis Of Rl And Adaptive Tensor Factorization.- 11 What Cannot Be Measured Cannot Be Controlled - Gauging Success With A/B Tests.- 12 Building A Recommendation Engine - The Xelopes Library.- 13 Last Words - Conclusion.- References.- Summary Of Notation.
Klappentext
¿¿¿¿Describing novel mathematical concepts for recommendation engines, Realtime Data Mining: Self-Learning Techniques for Recommendation Engines features a sound mathematical framework unifying approaches based on control and learning theories, tensor factorization, and hierarchical methods. Furthermore, it presents promising results of numerous experiments on real-world data.¿ The area of realtime data mining is currently developing at an exceptionally dynamic pace, and realtime data mining systems are the counterpart of today's ¿classic¿ data mining systems. Whereas the latter learn from historical data and then use it to deduce necessary actions, realtime analytics systems learn and act continuously and autonomously. In the vanguard of these new analytics systems are recommendation engines. They are principally found on the Internet, where all information is available in realtime and an immediate feedback is guaranteed. n nThis monograph appeals to computer scientists and specialists in machine learning, especially from the area of recommender systems, because it conveys a new way of realtime thinking by considering recommendation tasks as control-theoretic problems. Realtime Data Mining: Self-Learning Techniques for Recommendation Engines will also interest application-oriented mathematicians because it consistently combines some of the most promising mathematical areas, namely control theory, multilevel approximation, and tensor factorization.
Specifically addresses recommendation engines from a mathematically rigorous viewpoint
n
Discusses a control-theoretic framework for recommendation engines
n
Provides applications to a number of areas within engineering and computer science
n
