Publications and papers accepted for publication:

  • Predicting stock market indices movements. In Costantino, C.M. (Ed.), Computational Finance & its
    Applications, WIT Press, 2004, with Arnulfo Rodriguez. (PDF).

Abstract: This paper examines the extent to which the daily movements of three large emerging markets
stock indices are predictable. Lagged technical indicators are used as explanatory variables. In the analysis
we employed seven classification techniques and assessed the discriminatory power of the classifiers through
area under the receiver operating characteristic (ROC) curve. The results show that the daily movements of the
three indices are better predictable than random. After taking into account the bias induced by non-syschronous
price quotations, a trading system with break-even costs is simulated. The non-random classifiers yield returns
above those of both random walk and contrarian invesment strategies. No inefficiency is found due to the fact
that relatively low break-even transaction costs are enough to eliminate the sources of trading profits.  

Abstract: This paper extends the existing literature on empirical research in the field of sovereign debt.
To the authors’ knowledge, only one study in the area of sovereign debt has used a variety of statistical
methodologies to test the reliability of their predictions and to compare their performance against one another.
However, those comparisons across models have been made in terms of different probability cutoff points
and mean squared errors. Moreover, the issue of interpretability has not been addressed in terms of
interactions among explanatory variables with their correspondent debt rescheduling threshold level.
The areas under the Receiver Operating Characteristic (ROC) curves are used to compare the discrimination
power of statistical models. This paper tests Logit, MARS, Tree-based and Neural Network models.
Analyses of the relative importance of variables and deviance were done. All of the models rank the previous
payment history as the most important explanatory variable.

Abstract: In this paper we propose a new approach to evaluate the predictable components in stock indices using a
boosting-based classification technique, and we use this method to examine causality among the three main stock market
indices in the world during periods of large positive and negative price changes. The empirical evidence seems to indicate
that the Standard & Poors 500 index contains incremental information that is not present in either the FTSE 100 index or the
Nikkei 225 index, and that could be used to enhance the predictability of the large positive and negative returns in the three
main stock market indices in the world. This in turn would suggest a causality relationship running from the Standard &
Poors 500 index to both the FTSE 100 and the Nikkei 225 indices.

Working papers:

Abstract: We examine the relation between monthly stock returns and lagged publicly available information. Our primary
objective is to determine whether the variables proposed in the literature to predict the equity premium contain incremental
information to an investor. We find that certain variables do provide incremental information and may have some practical
value. Although this not necessarily imply that return-forecasting models may be used to predict future stock returns, some
model specifications may be used to predict future stock movements.

Abstract: We use a machine learning algorithm called Adaboost to find direction-of-change patterns for
the S&P 500 index using daily prices from 1962 to 2004. The patterns are able to identify periods to take long
and short positions in the index. This result, however,can largely be explained by first-order serial correlation in stock index

         Stock Movement Predictability and Classifier Induction, working paper. (PDF)

Abstract: This paper uses classifier induction to categorize the predictable components in stock returns
according to the particular movements they can actually predict. We document empirical results that suggest
past returns can be used to
(a) discriminate either absolute, or negative, or positive large returns from
the rest of stock movements regardless of whether or not returns exhibit low-order serial correlation,
(b) discriminate up from down movements only when such returns are serially correlated.

Abstract: The choice of monetary policy is the most important concern of central banks, but this choice is always
confronted with two relevant aspects of economic policy: parameter instability and model uncertainty. This paper
deals with both types of uncertainty and shows that recursive thick modeling is a better approximation to the recent
historical nominal interest rates in Mexico than both recursive thin modeling and models with a low penalty on
interest rate variability. We complement previous work by evaluating the usefulness of  both recursive thick
modeling and recursive thin modeling in terms of direction-of-change forecastability. The results show a policy
maker who cares about inflation and output stabilization the same for downward movements in nominal
interest rates. Furthermore, our results suggest a policy maker with a higher preference for inflation
stabilization for upward movements in nominal interest rates.
Pedro N. Rodriguez'- Home page