|
on Forecasting |
| By: | Steven Lehrer; Tian Xie |
| Abstract: | Substantial excitement currently exists in industry regarding the potential of using analytic tools to measure sentiment in social media messages to help predict individual reactions to a new product, including movies. However, the majority of models subsequently used for forecasting exercises do not allow for model uncertainty. Using data on the universe of Twitter messages, we use an algorithm that calculates the sentiment regarding each film prior to, and after its release date via emotional valence to understand whether these opinions affect box office opening and retail movie unit (DVD and Blu-Ray) sales. Our results contrasting eleven different empirical strategies from econometrics and penalization methods indicate that accounting for model uncertainty can lead to large gains in forecast accuracy. While penalization methods do not outperform model averaging on forecast accuracy, evidence indicates they perform just as well at the variable selection stage. Last, incorporating social media data is shown to greatly improve forecast accuracy for box-office opening and retail movie unit sales. |
| JEL: | C52 C53 M21 |
| Date: | 2016–12 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:22959&r=for |
| By: | Pantelis Promponas; David Alan Peel |
| Abstract: | Exchange rate forecasting has become an arena for many researchers the last decades while predictability depends heavily on several factors such as the choice of the fundamentals, the econometric model and the data form. The aim of this paper is to assess whether modelling time-variation and other forms of instabilities may improve the forecasting performance of the models. Paper begins with a brief critical review of the recently developed exchange rate forecasting models and continues with a real-time forecasting race between our fundamentals-based models, a DSGE model, estimated with Bayesian techniques and the benchmark random walk model without drift. Results suggest that models accounting for non-linearities may generate poor forecasts relative to more parsimonious and linear models. |
| Keywords: | Forecasting exchange rate, Exchange rate literature, Instability, Taylor rule, PPP, UIP, Money supply, Real-time estimation, Time-Varying models, DSGE model, Bayesian methods |
| JEL: | C53 E51 E52 F31 F37 G17 |
| Date: | 2016 |
| URL: | http://d.repec.org/n?u=RePEc:lan:wpaper:144439514&r=for |
| By: | László Békési (Magyar Nemzeti Bank, Central Bank of Hungary); Csaba Köber (OG Research); Henrik Kucsera; Tímea Várnai (Magyar Nemzeti Bank, Central Bank of Hungary); Balázs Világi (Magyar Nemzeti Bank, Central Bank of Hungary) |
| Abstract: | The lessons of the financial and macroeconomic crisis of 2007-2008 made the development of a new macroeconomic forecas ting model necessary in the MNB. The model represents a small open economy. It is based on the DSGE philosophy but it deviates from it at several points. The new features of the model, compared to previous forecasting models of the MNB, are that the debt constraint and the heterogeneity of households and financial accelerator mechanism through the financing constraints of the firms appear. From methodological point of view, it is important that the model deviates from ra??onal expectation hypothesis at several points and treats expectations pragmatically and flexibly. The model parameters are calibrated according to experts’ experience and SVAR estimations. The properties of the calibrated model are studied by impulse responses analysis, and the model fits into the MNB’s forecasting framework successfully. |
| Keywords: | DSGE models, forecasting, precautionary motive, buffer stock model, heterogeneous households, financial accelerator, non-rational expectations. |
| JEL: | E21 E27 E31 E37 E44 E52 |
| Date: | 2016 |
| URL: | http://d.repec.org/n?u=RePEc:mnb:wpaper:2016/4&r=for |
| By: | Richard Gerlach; Chao Wang |
| Abstract: | A new model framework called Realized Conditional Autoregressive Expectile (Realized-CARE) is proposed, through incorporating a measurement equation into the conventional CARE model, in a manner analogous to the Realized-GARCH model. Competing realized measures (e.g. Realized Variance and Realized Range) are employed as the dependent variable in the measurement equation and to drive expectile dynamics. The measurement equation here models the contemporaneous dependence between the realized measure and the latent conditional expectile. We also propose employing the quantile loss function as the target criterion, instead of the conventional violation rate, during the expectile level grid search. For the proposed model, the usual search procedure and asymmetric least squares (ALS) optimization to estimate the expectile level and CARE parameters proves challenging and often fails to convergence. We incorporate a fast random walk Metropolis stochastic search method, combined with a more targeted grid search procedure, to allow reasonably fast and improved accuracy in estimation of this level and the associated model parameters. Given the convergence issue, Bayesian adaptive Markov Chain Monte Carlo methods are proposed for estimation, whilst their properties are assessed and compared with ALS via a simulation study. In a real forecasting study applied to 7 market indices and 2 individual asset returns, compared to the original CARE, the parametric GARCH and Realized-GARCH models, one-day-ahead Value-at-Risk and Expected Shortfall forecasting results favor the proposed Realized-CARE model, especially when incorporating the Realized Range and the sub-sampled Realized Range as the realized measure in the model. |
| Date: | 2016–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1612.08488&r=for |