Download Online portfolio selection : principles and algorithms by Hoi, Steven C. H.; Li, Bin PDF

By Hoi, Steven C. H.; Li, Bin

Show description

Read or Download Online portfolio selection : principles and algorithms PDF

Similar machine theory books

Numerical computing with IEEE floating point arithmetic: including one theorem, one rule of thumb, and one hundred and one exercises

Are you acquainted with the IEEE floating element mathematics commonplace? do you want to appreciate it larger? This booklet supplies a huge assessment of numerical computing, in a ancient context, with a distinct specialise in the IEEE regular for binary floating aspect mathematics. Key rules are built step-by-step, taking the reader from floating element illustration, adequately rounded mathematics, and the IEEE philosophy on exceptions, to an realizing of the the most important ideas of conditioning and balance, defined in an easy but rigorous context.

Robustness in Statistical Pattern Recognition

This booklet is worried with vital difficulties of sturdy (stable) statistical pat­ tern acceptance whilst hypothetical version assumptions approximately experimental information are violated (disturbed). trend popularity concept is the sphere of utilized arithmetic during which prin­ ciples and techniques are developed for class and id of gadgets, phenomena, tactics, events, and indications, i.

Bridging Constraint Satisfaction and Boolean Satisfiability

This ebook presents an important step in the direction of bridging the components of Boolean satisfiability and constraint delight via answering the query why SAT-solvers are effective on yes periods of CSP situations that are tough to resolve for normal constraint solvers. the writer additionally provides theoretical purposes for selecting a specific SAT encoding for a number of very important sessions of CSP cases.

A primer on pseudorandom generators

A clean examine the query of randomness was once taken within the conception of computing: A distribution is pseudorandom if it can't be uncommon from the uniform distribution via any effective strategy. This paradigm, initially associating effective strategies with polynomial-time algorithms, has been utilized with admire to quite a few common periods of distinguishing systems.

Additional resources for Online portfolio selection : principles and algorithms

Example text

M1 is named as Uniform Constant Rebalanced Portfolios (UCRP). Another special CRP is the optimal offline† CRP strategy, whose portfolio can be calculated as n b = arg max Sn (CRP(b)) = arg max bn ∈ b∈ m m b xt , t=1 which is convex and can be efficiently solved. The CRP with b is denoted as Best Constant Rebalanced Portfolios (BCRPs), which achieve a final cumulative wealth as Sn (BCRP) = max Sn (CRP(b)) = Sn (CRP(b )) b∈ m Note that BCRP is a hindsight strategy, which can only be calculated with complete market sequences.

Helmbold et al. (1998) proposed the EG strategy, which is based on the same algorithm for mixture estimation (Helmbold et al. 1997). 2, EG adopts relative entropy as its regularization term, that is, m R(b, bt ) = bi log i=1 bi . bt,i EG’s formulation is convex in b; however, it is hard to solve since the log function is nonlinear. Thus, the authors adopted log’s first-order Taylor expansion at bt , that is, log b · xt ≈ log(bt · xt ) + xt (b − bt ). bt · xt Then the nonlinear log term becomes linear and the optimization is easy to solve.

Finally, we introduce the idea of how to evaluate a strategy’s performance. Specifically, this chapter is organized as follows. 1 formally formulates the OLPS task as a sequential decision problem. 2 relaxes the transaction costs and margin buying constraints. 3 introduces several evaluation metrics for the task. 4 summarizes this chapter. † At the t-th period (t = 1, . . , n), the asset (close) prices are represented by a vector pt ∈ Rm + , and each element pt,i , i = 1, . . , m, represents the close price of asset i.

Download PDF sample

Rated 4.68 of 5 – based on 29 votes