Machine learning and big data with kdb+/q / Jan Novotny, Paul A. Bilokon, Aris Galiotos, Frédéric Déléze.

Includes bibliographical references and index.

Fundamentals of the q programming language -- Dictionaries and tables : the q fundamentals -- Functions -- Editors and other tools -- Debugging q code -- Splayed and partitioned tables -- Joins -- Parallelisation -- Data cleaning and filtering -- Parse trees -- A few use cases -- Basic overview of statistics -- Linear regression -- Time series econometrics -- Fourier transform -- Eigensystem and PCA -- Outlier detection -- Simulating asset prices -- Basic principles of machine learning -- Linear regression with regularisation -- Nearest neighbours -- Neural networks -- AdaBoost with stumps -- Trees -- Forests -- Unsupervised machine learning : the Apriori algorithm -- Processing information -- Towards AI : Monte Carlo tree search -- Econophysics : the agent-based computational models -- Epilogue:

"The book will start with an examination of the foundations of kdb+/q and will proceed to consider the practicalities of dealing with real high-frequency data, and then demonstrate how kdb+/q can be used to solve econometric problems of practical importance. The exploratory journey of the language follows the path the high-frequency quants undertake every time they develop a working strategy: from data description and summary statistics to basic regression methods and cointegration, from volatility estimation and modelling to optimal execution, from market impact and microstructure analyses to advanced machine learning techniques including the neural networks"-- Provided by publisher.

Description based on print version record and CIP data provided by publisher; resource not viewed.