Angel Samaniego

A

Levels of economic concentration for the Treynor-Black model

Análisis Económicos Profesionales S.A. de C.V.

May 2023

Se estudian los niveles de concentración económica en portafolios de inversión mediante el índice de Herfindahl (HI). De portafolios formados con el modelo de Treynor-Black (TB), solo en su parte activa. Utilizando los componentes incluidos en el Dow Jones Industrial Average (DJIA) entre 2000-2020. Aunque el modelo TB es superior al desempeño al DJIA, presenta períodos de inversión con un bajo HI. Los portafolios con HI>=0.885 (entre 11 a 17 activos) no superan al desempeño del DJIA. Al contrario, cuando los portafolios de TB con HI<0.05 (un solo activo, 20.7% del total de observaciones) superan el desempeño del DJIA y al resto de combinaciones con HI>0.05. Teniendo un rendimiento promedio del 17.1%, con una probabilidad del 83.2% de supera

R

Semi-variance optimization for the components of the Dow Jones Industrial Average index

Revista en Contaduría y Administración

Apr 2023

This study contributes to passive portfolio management by comparing four ways for asset allocation. Index investing, mean-variance optimization, equal-weighting and semi-variance optimization are compared as part of the investment strategy aimed at outperforming the Dow Jones Industrial Average (DJIA). The best way to allocate assets was the optimization of portfolios looking for the minimum semi-variance. Yield spreads below the performance of the DJIA and the components of this index are used to the semi-variance. The best strategy has a 65.2% probability of outperforming the DJIA annual return. 5,134 simulations are run between 2000-2020. An abnormal annual return of 0.42% and a beta of 0.95 obtained with the CAPM was achieved.

A

CAPM-alpha estimation with robust regression vs. linear regression

Análisis Económicos Profesionales S.A. de C.V.

Jan 2023

El análisis de regresión por mínimos cuadrados ordinarios busca encontrar la relación entre variables bajo ciertos supuestos. Y en caso de no cumplirse estos, se dice que sus resultados no son robustos. La regresión robusta mediante la optimización busca cumplir estos supuestos. Se contrastan ambos métodos de regresión utilizando la siguiente premisa: el desempeño (CAPM-alpha) pasado es un buen estimador del desempeño futuro. En el periodo de estudio se encontraron resultados muy similares, donde la regresión lineal sobresale sobre la regresión robusta. Empíricamente se utilizan portafolios activos mediante la metodología de Treynor-Black entre 2000-2020 para contrastar los métodos de regresión.

C

Is the omega ratio a good portfolio optimization criterion?

Contaduría Y Administración ISSN: 0186-1042

Oct 2022

The Omega ratio has been widely used in the literature to optimize and search for good performance in investment portfolios. It considers both the downside and upside potential of the portfolio with respect to a predetermined threshold, which can be fixed or time varying. Mixed results have been obtained in different markets and periods. And when combined with other performance or risk measures, its results can be improved. The proposed model restricts the omega ratio to a value of less than 470, a maximum investment in each asset of 15%, with a target annual return equal to the return of the Dow Jones Industrial Average (DJIA) among the assets that make up the index. In the study period (2000-2020, rolling window with annual return per day

P

What Is a Right Metric to Measure Exchange Rate Forecasting Models' Accuracy?

Proceedings of The th International Conference on Future of Business Management and Economics Rome Italy

May 2022

The most common metric used to measure financial model errors is mean square error (MSE). This metric measures the distance between the actual closing price and the forecasted price at one point in time. However, during the day, actual prices are constantly fluctuating, therefore an additional metric is proposed: correct price percentage (CPP) metric, this last metric is used to measure the accuracy of the projected prices within a lower and upper limit within a period; as a result, as long as, the forecasted prices are within that range, the forecasted price will be correct. Our work compares those two metrics: mean square error and correct price percentage for different forecasting models created through an Artificial Neural Network (ANN)

P

Comparing Different Optimization Error Functions in An Artificial Neural Network For Exchange Rate Forecasting Models

Proceedings of The th International Conference on Future of Business Management and Economics Rome Italy

May 2022

The most common optimization factor used in Artificial Neural Networks (ANN) is Mean Square Error (MSE). During this research, we propose a different approach for error function to optimize the models: adjusted mean square error (AMSE), adjusted mean absolute error (AMAE) and Correct Price Percentage (CPP). We will create an ANN exchange rate forecasting model using different performance functions, where we will be comparing our proposed error functions: CPP, AMAE and AMSE, against the traditional error functions: MSE, mean absolute error (MAE), sum absolute error (SAE), sum squared error (SSE) and cross-entropy (CE). We will measure the errors of the models using CPP and MSE as metrics. One of the goals of a models, is not only predict the

N

Leading macroeconomic indicators for a dynamic investment strategy

Nova Scientia

Mar 2022

En este documento se desarrolla un modelo de optimización de la cartera en el largo plazo, mediante el uso de indicadores económicos (CLI y BCI). De esta manera un portafolio de inversión se ajustará a los movimientos del ciclo económico, mitigando su riesgo ante posibles caídas. El contraste del modelo propuesto se realizó en México entre 1998-2021. La estrategia activa realiza inversiones en renta fija (Certificados de la Tesorería, CETES) y en el índice de mercado (Índice de Precios y Cotizaciones, IPC), mediante operaciones del 25% del capital en decisiones mensuales. La estrategia de inversión dinámica supera al índice de mercado en un 4.3% en el periodo anal

R

Passive portfolio management by indexing: a performance analysis of high, medium, and low capitalization indices in Mexi

Revista de Métodos Cuantitativos para la Economía y Empresa

Dec 2018

In a passive investing strategy through indexation, the portfolio performance will depend largely on the ability to choose the best index. In this paper, we study the performance of four of the main stock indices in Mexico with the intention of selecting the best one for a passive investing strategy. To solve this question, departing from the Sortino ratio, a definition of probability of success substitutes the average excess return over a target and the use of the maximum standard deviation on the negative target return. The new performance measure gives different results to those of the traditional Sortino ratio, with the IPC large cap being the best index for a passive strategy, in terms of risk-reward ratio and return target.

R

Testing the Capital Asset Pricing Model using the Kalman Filter: Empirical Evidence from the Mexican Stock Market

Recent Topics in Time Series and Finance Theory and Applications in Emerging Markets Universidad de Guadalajara

Mar 2018

The Capital Asset Pricing Model (CAPM) widely used for the valuation of financial assets may have periods of low explanation (low R-square). For those periods, the factor models have a low confidence. The Kalman filter is able to sort out the noise that often have the data, such as the high volatility of the time series in financial markets. This chapter presents empirical evidence of CAPM model calculation using the Kalman filter from the Mexican financial market data

J

Factores que influyen sobre la conducta de una persona frente al riesgo de emprender un negocio en América Latina.

Journal of Business

Nov 2016

El desempleo y la baja calidad de los empleos existentes, han creado la necesidad de emprender y pasar de ser empleado a emprendedor. Sin embargo, existen algunos factores que caracterizan a este comportamiento. La presente investigación identifica algunos de los factores que incrementan en una persona el riesgo de emprender un negocio en América Latina. Los principales factores que influyen en este comportamiento son: la experiencia, el conocimiento, la habilidad y la edad entre las once variables utilizadas en el periodo 2009–2011. Los modelos de redes neuronales utilizados clasifican a la variable dependiente (miedo al fracaso) con un porcentaje de acierto del 68% en el periodo de estudio.

About

Detail

Timeline

Résumé