Estimating expected returns with forecast combinations

dc.contributor.advisorGómez Portilla, Karoll
dc.contributor.authorRichter, Robert
dc.contributor.researchgroupGrupo Interdisciplinario en Teoría e Investigación Aplicada en Ciencias Económicasspa
dc.date.accessioned2021-09-03T22:41:41Z
dc.date.available2021-09-03T22:41:41Z
dc.date.issued2021-09-03
dc.descriptionIlustracionesspa
dc.description.abstractThis thesis proposes to apply forecasts produced by expert aggregation as novel predictor of expected returns to 2 different portfolio strategies: 1) mean-variance as proposed by (Markowitz, 1952) and 2) shrinkage of the covariance matrix S as in (Ledoit, 2004). Experts were built by generating forecasts with quantile regression as in generalized random forests and automatised versions of exponential smoothing and ARIMA. This study evaluates the predictive performance of two forecast combination algorithms 1) ML-Prod and 2) ML-Poly using a simulation study, before applying the superior method to a portfolio scenario. After evaluating prediction accuracy, the superior ML-Poly algorithm was chosen to forecast expected returns and showed promising out-of-sample results for the considered portfolios, returning superior values for the selected performance parameter and only marginal inferior results in terms of turnover ratio. Using the simulation study, the results of the portfolios were also validated.eng
dc.description.abstractEsta tesis propone aplicar los pronósticos generados por la agregación de expertos como un novedoso predictor de los rendimientos esperados a 2 estrategias de portafolio diferentes: 1) Mean-Variance como propone (Markowitz, 1952) y 2) contracción de la matriz de covarianza S como en (Ledoit, 2004). Los expertos se construyeron generando pronósticos con Quantile Regression de Generalized Random Forests y versiones automatizadas de Exponential Smoothing y ARIMA. Este estudio evalúa la precisión de los pronósticos de dos algoritmos de agregación de expertos 1) ML-Prod y 2) ML-Poly mediante un estudio de simulación, antes de aplicar el método superior a un portafolio diversificado. Después de evaluar la precisión de los pronósticos, se eligió el algoritmo superior ML-Poly para pronosticar los rendimientos esperados y mostró resultados prometedores fuera de la muestra para los portafolios considerados, devolviendo valores superiores para los parámetros de rendimiento seleccionados y resultados inferiores marginales en términos de ratio de rotación. Mediante el estudio de simulación, también se validaron los resultados de los portafolios. (Texto tomado de la fuente).spa
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagister en Administraciónspa
dc.description.methodsEstudio Empiricospa
dc.description.notesMención Meritoriaspa
dc.description.notesTesis de grado presentada como requisito parcial para optar al título de: Magister en Administración de Negocios (Universidad Europea de Viadrina)spa
dc.description.researchareaSeminario de Investigación IIspa
dc.format.extentxii, 48 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/80095
dc.language.isoengspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotáspa
dc.publisher.departmentEscuela de Administración y Contaduría Públicaspa
dc.publisher.facultyFacultad de Ciencias Económicasspa
dc.publisher.placeBogotá, Colombiaspa
dc.publisher.programBogotá - Ciencias Económicas - Maestría en Administraciónspa
dc.relation.referencesAmit, Y. & Geman, D. (1997). Shape quantization and recognition with randomized trees. 0899-7667, 9 (7), 1545–1588. https://doi.org/10.1162/neco.1997.9.7.1545
dc.relation.referencesAnderson, B. D. O. (2012). Optimal filtering. Dover Publications.
dc.relation.referencesAoki, M. & Havenner, A. (1991). State space modeling of multiple time series. Econometric Reviews, 10 (1), 1–59. https://doi.org/10.1080/07474939108800194
dc.relation.referencesArlot, S. & Genuer, R. (2014). Analysis of purely random forests bias. https://arxiv.org/pdf/1407.3939
dc.relation.referencesAthey, S., Tibshirani, J. & Wager, S. (2019). Generalized random forests. 0090-5364, 47 (2), 1148–1178. https://doi.org/10.1214/18-AOS1709
dc.relation.referencesBan, G.-Y., El Karoui, N. & Lim, A. E. B. (2018). Machine learning and portfolio optimiz ation, (64), 1136–1154.
dc.relation.referencesBiau, G. (2012). Analysis of a random forests model, (13), 1063–1095.
dc.relation.referencesBiau, G., Devroye, L. & Lugosi, G. (2008). Consistency of random forests and other averaging classifiers, (9), 2015–2033.
dc.relation.referencesBlum, A. & Mansour, Y. (2007). From external to internal regret. Journal of Machine Learning Research, 8 (47), 1307–1324.
dc.relation.referencesBox, G. E. P. & Jenkins, G. M. (1970). Time series analysis: Forecasting and control. Holden Day.
dc.relation.referencesBreiman, L. (1984). Classification and regression trees [Breiman, Leo, (author.)]. [Routledge].
dc.relation.referencesBreiman, L. (1996). Bagging predictors [PII: BF00058655]. 08856125, 24 (2), 123–140. https://doi.org/10.1007/BF00058655
dc.relation.referencesBreiman, L. (2001). Random forests [PII: 354300]. 08856125, 45 (1), 5–32. https://doi.org/10.1023/A:1010933404324
dc.relation.referencesBrockwell, P. J. & Davis, R. A. (2006). Time series: Theory and methods (2nd ed., correc ted.). New York, Springer.
dc.relation.referencesBuhlmann, P. & Yu, B. (2002). Analyzing bagging [PII: aos30n4r01]. 0090-5364, 30 (4), 927–961. https://doi.org/10.1214/aos/1031689014
dc.relation.referencesCesa-Bianchi, N. & Lugosi, G. (2006). Prediction, learning, and games. Cambridge University Press.
dc.relation.referencesCesa-Bianchi, N. & Lugosi, G. (2003). Potential-based algorithms in on-line prediction and game theory [PII: 5120299]. 08856125, 51 (3), 239–261. https://doi.org/10.1023/A:1022901500417
dc.relation.referencesAmit, Y. & Geman, D. (1997). Shape quantization and recognition with randomized trees. 0899-7667, 9 (7), 1545–1588. https://doi.org/10.1162/neco.1997.9.7.1545
dc.relation.referencesAnderson, B. D. O. (2012). Optimal filtering. Dover Publications.
dc.relation.referencesAoki, M. & Havenner, A. (1991). State space modeling of multiple time series. Econometric Reviews, 10 (1), 1–59. https://doi.org/10.1080/07474939108800194
dc.relation.referencesArlot, S. & Genuer, R. (2014). Analysis of purely random forests bias. https://arxiv.org/pdf/1407.3939
dc.relation.referencesAthey, S., Tibshirani, J. & Wager, S. (2019). Generalized random forests. 0090-5364, 47 (2), 1148–1178. https://doi.org/10.1214/18-AOS1709
dc.relation.referencesBan, G.-Y., El Karoui, N. & Lim, A. E. B. (2018). Machine learning and portfolio optimiz ation, (64), 1136–1154.
dc.relation.referencesBiau, G. (2012). Analysis of a random forests model, (13), 1063–1095.
dc.relation.referencesBiau, G., Devroye, L. & Lugosi, G. (2008). Consistency of random forests and other averaging classifiers, (9), 2015–2033.
dc.relation.referencesBlum, A. & Mansour, Y. (2007). From external to internal regret. Journal of Machine Learning Research, 8 (47), 1307–1324.
dc.relation.referencesBox, G. E. P. & Jenkins, G. M. (1970). Time series analysis: Forecasting and control. Holden Day.
dc.relation.referencesBreiman, L. (1984). Classification and regression trees [Breiman, Leo, (author.)]. [Routledge].
dc.relation.referencesBreiman, L. (1996). Bagging predictors [PII: BF00058655]. 08856125, 24 (2), 123–140. https://doi.org/10.1007/BF00058655
dc.relation.referencesBreiman, L. (2001). Random forests [PII: 354300]. 08856125, 45 (1), 5–32. https://doi.org/10.1023/A:1010933404324
dc.relation.referencesBrockwell, P. J. & Davis, R. A. (2006). Time series: Theory and methods (2nd ed., correc ted.). New York, Springer.
dc.relation.referencesBuhlmann, P. & Yu, B. (2002). Analyzing bagging [PII: aos30n4r01]. 0090-5364, 30 (4), 927–961. https://doi.org/10.1214/aos/1031689014
dc.relation.referencesCesa-Bianchi, N. & Lugosi, G. (2006). Prediction, learning, and games. Cambridge University Press.
dc.relation.referencesCesa-Bianchi, N. & Lugosi, G. (2003). Potential-based algorithms in on-line prediction and game theory [PII: 5120299]. 08856125, 51 (3), 239–261. https://doi.org/10.1023/A:1022901500413
dc.relation.referencesHyndman, R. J., Koehler, A. B., Ord, J. K. & Snyder, R. D. (2008). Forecasting with exponential smoothing: The state space approach. Berlin, Heidelberg, Springer. https://doi.org/10.1007/978-3-540-71918-2
dc.relation.referencesJagannathan, R. & Ma, T. (2003). Risk reduction in large portfolios: Why imposing the wrong constraints helps, 58 (4), 1651–1683. https://doi.org/10.1111/1540-6261.00580
dc.relation.referencesKoenker, R. (2005). Quantile regression [Koenker, Roger (VerfasserIn)]. Cambridge, Cam bridge University Press. https://doi.org/10.1017/CBO9780511754098
dc.relation.referencesKoenker, R. & Bassett, G. (1978). Regression quantiles [Econometrica, 46(1), 33]. Econo metrica, 46 (1), 33. https://doi.org/10.2307/1913643
dc.relation.referencesKwiatkowski, D., Phillips, P. C., Schmidt, P. & Shin, Y. (1992). Testing the null hypothesis of stationarity against the alternative of a unit root [PII: 030440769290104Y]. Journal of Econometrics, 54 (1-3), 159–178. https://doi.org/10.1016/0304-4076(92)90104-y
dc.relation.referencesLandau, S. & Chis Ster, I. (2010). Cluster analysis: Overview, 72–83. https://doi.org/10.1016/B978-0-08-044894-7.01315-4
dc.relation.referencesLedoit, O. & Wolf, M. (2004). Honey, i shrunk the sample covariance matrix, (4), 110–119. https://doi.org/10.3905/jpm.2004.110
dc.relation.referencesLin, Y. & Jeon, Y. (2006). Random forests and adaptive nearest neighbors. 0162-1459, 101 (474), 578–590. https://doi.org/10.1198/016214505000001230
dc.relation.referencesLintner, J. (1965). The valuation of risk assets and the selection of risky investments in stock portfolios and capital budgets. 00346535, 47 (1), 13. https://doi.org/10.2307/1924119
dc.relation.referencesLittlestone, N. & Warmuth, M. K. (1994). The weighted majority algorithm [PII: S0890540184710091]. Information and Computation, 108 (2), 212–261. https://doi.org/10.1006/inco.1994.1009
dc.relation.referencesLopez de Prado, M. (2016). Building diversified portfolios that outperform out of sample. The Journal of Portfolio Management, 42 (4), 59–69. https://doi.org/10.3905/jpm.2016.42.4.059
dc.relation.referencesMakridakis, S. & Hibon, M. (2000). The m3-competition: Results, conclusions and implica tions [PII: S0169207000000571]. International Journal of Forecasting, 16 (4), 451–476. https://doi.org/10.1016/S0169-2070(00)00057-1
dc.relation.referencesMarkowitz, H. M. (1952). Portfolio selection, (Vol. 7, No. 1), 77–91.
dc.relation.referencesMcAndrew, T., Wattanachit, N., Gibson, G. C. & Reich, N. G. (2019). Aggregating predic tions from experts: A scoping review of statistical methods, experiments, and applica tions [https://github.com/tomcm39/AggregatingExpertElicitedDataForPrediction v0.2: updated funding info]. https://arxiv.org/pdf/1912.11409
dc.relation.referencesMeinshausen, N. (2006). Quantile regression forests. Journal of Machine Learning Research, 7 (Jun), 983–999.
dc.relation.referencesMentch, L. & Hooker, G. (2016). Quantifying uncertainty in random forests via confidence intervals and hypothesis tests, (17), 1–41.
dc.relation.referencesMerton, R. C. (1980). On estimating the expected return on the market: An exploratory investigation, (8), 323–361
dc.relation.referencesMossin, J. (1966). Equilibrium in a capital asset market, (34), 768–783.
dc.relation.referencesNewey, W. K. (1994). The asymptotic variance of semiparametric estimators, 62 (6), 1349. https://doi.org/10.2307/2951752
dc.relation.referencesSchmidhuber, J. (2014). Deep learning in neural networks: An overview, (61), 85–117.
dc.relation.referencesScornet, E., Biau, G. & Vert, J.-P. (2015). Consistency of random forests. 0090-5364, 43 (4), 1716–1741. https://doi.org/10.1214/15-AOS1321
dc.relation.referencesSharpe, W. F. (1964). Capital asset prices: a theory of market equilibirium under conditions of risk, (19), 425–442.
dc.relation.referencesSharpe, W. F. (1970). Portolio theory and capital markets. McGraw-Hill.
dc.relation.referencesStaniswalis, J. G. (1989). The kernel estimate of a regression function in likelihood-based models. 0162-1459, 84 (405), 276. https://doi.org/10.2307/2289874
dc.relation.referencesStone, C. J. (1977). Consistent nonparametric regression, (5), 595–620.
dc.relation.referencesTibshirani, R. & Hastie, T. (1987). Local likelihood estimation. 0162-1459, 82 (398), 559–567. https://doi.org/10.1080/01621459.1987.10478466
dc.relation.referencesTimmermann, A. (2006). Chapter 4 forecast combinations. In G. Elliott, C. Granger
dc.relation.referencesVovk, V. (1998). A game of prediction with expert advice [PII: S0022000097915567]. Journal of Computer and System Sciences, 56 (2), 153–173. https://doi.org/10.1006/jcss. 1997.1556
dc.relation.referencesWager, S. & Athey, S. (2018). Estimation and inference of heterogeneous treatment effects using random forests. 0162-1459, 113 (523), 1228–1242. https://doi.org/10.1080/01621459.2017.1319839
dc.relation.referencesWager, S. & Walther, G. (2015). Adaptive concentration of regression trees, with application to random forests. https://arxiv.org/pdf/1503.06388
dc.relation.referencesZeileis, A., Hothorn, T. & Hornik, K. (2008). Model-based recursive partitioning. 1061-8600, 17 (2), 492–514. https://doi.org/10.1198/106186008X31933
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial-CompartirIgual 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/spa
dc.subject.ddc330 - Economíaspa
dc.subject.ecmFinancial Forecasting and Simulationeng
dc.subject.ecmPredicción y simulación financieraspa
dc.subject.jelC53 Forecasting Models; Simulation Methods
dc.subject.lembEconomic forecasting
dc.subject.lembPronóstico de la economía
dc.subject.lembForecasting techniques
dc.subject.lembTécnicas de predicción
dc.subject.otherFinancial Forecasting and Simulationeng
dc.subject.otherPredicción y simulación financieraspa
dc.subject.proposalShrinkageeng
dc.subject.proposalDecision tresseng
dc.subject.proposalExpert aggregationeng
dc.subject.proposalMedia-varianzaspa
dc.subject.proposalMean-varianceeng
dc.subject.proposalGeneralized random foresteng
dc.subject.proposalAutomatic arimaeng
dc.subject.proposalPortfolio optimisationeng
dc.subject.proposalExponential smoothingeng
dc.subject.proposalÁrboles de decisionspa
dc.subject.proposalArima automatizadospa
dc.subject.proposalAgregación de expertosspa
dc.subject.proposalOptimización de portafoliosspa
dc.titleEstimating expected returns with forecast combinationseng
dc.title.translatedEstimación de los rendimientos esperados con combinaciones de previsionesspa
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentPúblico generalspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
Tesis_RobertRichter.pdf
Tamaño:
905.16 KB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Administración

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.87 KB
Formato:
Item-specific license agreed upon to submission
Descripción: