Data Mining in Finance: Advances in Relational and Hybrid by Boris Kovalerchuk

By Boris Kovalerchuk

Data Mining in Finance offers a accomplished evaluation of significant algorithmic ways to predictive information mining, together with statistical, neural networks, ruled-based, decision-tree, and fuzzy-logic tools, after which examines the suitability of those ways to monetary facts mining. The publication focuses particularly on relational facts mining (RDM), that's a studying procedure in a position to research extra expressive ideas than different symbolic methods. RDM is hence greater suited to monetary mining, since it is ready to make higher use of underlying area wisdom. Relational information mining additionally has a greater skill to provide an explanation for the came across ideas - a capability serious for averting spurious styles which necessarily come up whilst the variety of variables tested is huge. the sooner algorithms for relational facts mining, often referred to as inductive common sense programming (ILP), be afflicted by a relative computational inefficiency and feature quite restricted instruments for processing numerical info.
Data Mining in Finance introduces a brand new method, combining relational facts mining with the research of statistical importance of stumbled on ideas. This reduces the hunt area and hurries up the algorithms. The publication additionally provides interactive and fuzzy-logic instruments for `mining' the data from the specialists, extra lowering the quest house.
Data Mining in Finance encompasses a variety of functional examples of forecasting S&P 500, trade premiums, inventory instructions, and score shares for portfolio, permitting readers to begin development their very own versions. This publication is a superb reference for researchers and execs within the fields of man-made intelligence, computing device studying, info mining, wisdom discovery, and utilized mathematics.

Show description

Read or Download Data Mining in Finance: Advances in Relational and Hybrid Methods PDF

Best data mining books

Transactions on Rough Sets XIII

The LNCS magazine Transactions on tough units is dedicated to the whole spectrum of tough units similar matters, from logical and mathematical foundations, via all elements of tough set concept and its purposes, similar to information mining, wisdom discovery, and clever details processing, to kinfolk among tough units and different techniques to uncertainty, vagueness, and incompleteness, comparable to fuzzy units and thought of proof.

Knowledge Discovery Practices and Emerging Applications of Data Mining: Trends and New Domains

Fresh advancements have greatly elevated the amount and complexity of knowledge on hand to be mined, major researchers to discover new how one can glean non-trivial facts immediately. wisdom Discovery Practices and rising purposes of information Mining: traits and New domain names introduces the reader to contemporary examine actions within the box of knowledge mining.

Requirements Engineering in the Big Data Era: Second Asia Pacific Symposium, APRES 2015, Wuhan, China, October 18–20, 2015, Proceedings

This publication constitutes the complaints of the second one Asia Pacific standards Engineering Symposium, APRES 2015, held in Wuhan, China, in October 2015. The nine complete papers offered including three instrument demos papers and one brief paper, have been conscientiously reviewed and chosen from 18 submissions. The papers take care of quite a few elements of necessities engineering within the giant info period, equivalent to computerized specifications research, requisites acquisition through crowdsourcing, requirement techniques and standards, necessities engineering instruments.

Additional info for Data Mining in Finance: Advances in Relational and Hybrid Methods

Sample text

This approach has been used successfully with the AVO instance-based learning method for classification of court decisions with a scarce data set [Kovalerchuk et al, 1977]. Numerical Data Mining Models and Financial Applications 35 Case-based reasoning covers instance-based learning relaxing the requirement of embedding data into Euclidean space. Other presentation of data are permitted and alternative measures of closeness can be used [Mitchell, 1997]. Financial Time Series Forecasting using k-Nearest Neighbors Classification.

However, in financial markets, often time series like stock indices, foreign exchange trends and others are all nonstationary even for the short-term trend [Drake, Kim, 1997]. , 1990]. ARIMA models implicitly assume that a strong and relatively simple statistical regularity exists in a time series. Unfortunately, this is not a very re- alistic assumption for many financial time series. Therefore, the successful use of ARIMA is still an individual art rather than a regular procedure. Moreover, the possibility to present all actual regularities in one simple formula is questionable for many time series.

Below we describe machine learning paradigms using three components: – Knowledge representation, – Forecast performer, and – Learning mechanism. Knowledge representation sets a framework for representing prior knowledge. A forecast performer serves as a final product, generating a forecast from learned knowledge. A learning mechanism produces new knowledge and identifies parameters for the forecast performer using prior knowledge. Knowledge representation is the major characteristic used to distinguish five known paradigms [Langley, Simon, 1995]: 1.

Download PDF sample

Rated 4.96 of 5 – based on 39 votes