LEADER 05691nam 2200745 a 450 001 9910963401503321 005 20250923003152.0 010 $a9786613645944 010 $a9781280669019 010 $a1280669012 010 $a9781848168145 010 $a1848168144 035 $a(CKB)2550000000101563 035 $a(EBL)919109 035 $a(OCoLC)794328402 035 $a(SSID)ssj0000657160 035 $a(PQKBManifestationID)12291803 035 $a(PQKBTitleCode)TC0000657160 035 $a(PQKBWorkID)10635294 035 $a(PQKB)11137376 035 $a(MiAaPQ)EBC919109 035 $a(WSP)0000P818 035 $a(Au-PeEL)EBL919109 035 $a(CaPaEBR)ebr10563587 035 $a(CaONFJC)MIL364594 035 $a(Perlego)848133 035 $a(EXLCZ)992550000000101563 100 $a20120608d2012 uy 0 101 0 $aeng 135 $aurcn||||||||| 181 $ctxt 182 $cc 183 $acr 200 10$aMachine learning for financial engineering /$fLa?szlo? Gyo?rfi, Gyo?rgy Ottucsa?k, Harro Walk 205 $a1st ed. 210 $aLondon $cImperial College Press$d2012 215 $a1 online resource (261 p.) 225 1 $aAdvances in computer science and engineering: Texts ;$vv. 8 300 $aDescription based upon print version of record. 311 08$a9781848168138 311 08$a1848168136 320 $aIncludes bibliographical references and index. 327 $aContents; Preface; 1. On the History of the Growth-Optimal Portfolio M. M. Christensen; 1.1. Introduction and Historical Overview; 1.2. Theoretical Studies of the GOP; 1.2.1. Discrete Time; 1.2.2. Continuous-Time; 1.3. The GOP as an Investment Strategy; 1.3.1. Is the GOP Better? - The Samuelson Controversy; 1.3.2. Capital Growth and the Mean-Variance Approach; 1.3.2.1. Discrete time; 1.3.2.2. Continuous time; 1.3.3. How Long Does it Take for the GOP to Outperform other Portfolios?; 1.4. The GOP and the Pricing of Financial Assets and Derivatives; 1.4.1. Incomplete Markets 327 $a1.4.1.1. Utility-Based Pricing 1.4.1.2. The Minimal Martingale Measure; 1.4.1.3. Good-Deal Bounds; 1.4.2. A World Without a Risk-Neutral Measure; 1.5. Empirical Studies of the GOP; 1.5.1. Composition of the GOP; 1.5.1.1. Discrete-Time Models; 1.5.1.2. Continuous Time Models; 1.6. Conclusion; References; 2. Empirical Log-Optimal Portfolio Selections: A Survey L. Gyorfi, Gy. Ottucsak and A. Urban; 2.1. Introduction; 2.2. Constantly-Rebalanced Portfolio Selection; 2.2.1. Log-Optimal Portfolio for Memoryless Market Process; 2.2.2. Examples for the Constantly-Rebalanced Portfolio3 327 $a2.2.3. Semi-Log-Optimal Portfolio 2.3. Time-Varying Portfolio Selection; 2.3.1. Log-Optimal Portfolio for Stationary Market Process; 2.3.2. Empirical Portfolio Selection; 2.3.3. Regression Function Estimation; 2.3.4. Histogram-Based Strategy; 2.3.5. Kernel-Based Strategy; 2.3.6. Nearest-Neighbor-Based Strategy; 2.3.7. Numerical Results on Empirical Portfolio Selection; References; 3. Log-Optimal Portfolio-Selection Strategies with Proportional Transaction Costs L. Gyorfi and H. Walk; 3.1. Introduction; 3.2. Mathematical Setup: Investment with Proportional Transaction Cost 327 $a3.3. Experiments on Heuristic Algorithms.4. Growth-Optimal Portfolio Selection Algorithms; 3.5. Portfolio Selection with Consumption; 3.6. Proofs; References; 4. Growth-Optimal Portfolio Selection with Short Selling and Leverage M. Horvath and A. Urban; 4.1. Introduction; 4.2. Non-Leveraged, Long-Only Investment; 4.3. Short Selling; 4.3.1. No-Ruin Constraints; 4.3.2. Optimality Condition for Short Selling with Cash Account; 4.4. Long-Only Leveraged Investment; 4.4.1. No-Ruin Condition; 4.4.2. Kuhn-Tucker Characterization; 4.5. Short Selling and Leverage; 4.6. Experiments; References 327 $a5. Nonparametric Sequential Prediction of Stationary Time Series L. Gyorfi and Gy. Ottucsak5.1. Introduction; 5.2. Nonparametric Regression Estimation; 5.2.1. The Regression Problem; 5.2.2. Regression Function Estimation and L2 Error; 5.2.3. Partitioning Estimate; 5.2.4. Kernel Estimate; 5.2.5. Nearest-Neighbor Estimate; 5.2.6. Empirical Error Minimization; 5.3. Universally Consistent Predictions: Bounded Y; 5.3.1. Partition-Based Prediction Strategies; 5.3.2. Kernel-Based Prediction Strategies; 5.3.3. Nearest-Neighbor-Based Prediction Strategy; 5.3.4. Generalized Linear Estimates 327 $a5.4. Universally Consistent Predictions: Unbounded Y 330 $aThis volume investigates algorithmic methods based on machine learning in order to design sequential investment strategies for financial markets. Such sequential investment strategies use information collected from the market's past and determine, at the beginning of a trading period, a portfolio; that is, a way to invest the currently available capital among the assets that are available for purchase or investment. The aim is to produce a self-contained text intended for a wide audience, including researchers and graduate students in computer science, finance, statistics, mathematics, 410 0$aAdvances in computer science and engineering.$pTexts ;$vv. 8. 606 $aMachine learning 606 $aFinancial engineering 615 0$aMachine learning. 615 0$aFinancial engineering. 676 $a006.31 700 $aGyo?rfi$b La?szlo?$0441760 701 $aOttucsa?k$b Gyo?rgy$01848549 701 $aWalk$b Harro$f1939-$0736516 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910963401503321 996 $aMachine learning for financial engineering$94435665 997 $aUNINA