Many existing learning algorithms suffer from limited architectural depth and the locality of estimators, making it difficult to generalize from the test set and providing inefficient and biased estimators. Deep architectures have been shown to appropriately learn correlation structures in time series data. This paper compares the effectiveness of a deep feedforward Neural Network (DNN) and shallow architectures (e.g., Support Vector Machine (SVM) and one-layer NN) when predicting a broad crosssection of stock price indices in both developed and emerging markets. An extensive evaluation is undertaken, using daily, hourly, minute and tick level data related to thirty-four financial indices from 32 countries across six years. Our evaluation results show a considerable advantage from training deep (cf. shallow) architectures, using a rectifier linear (RELU) activation function, across all thirty-four markets when 'minute' data is used. However, the predictive performance of DNN was not significantly better than that of shallower architectures when using tick level data. This result suggests that when training a DNN algorithm, the predictive accuracy peaks, regardless of training size. We also examine which activation function works best for stock price index data. Our results demonstrate that the RELU activation function performs better than TANH across all markets and time horizons when using DNN to predict stock price indices.
We model the effect of online information search across mobile (smartphone and tablet) and nonmobile (personal computer [PC], both desktop and laptop) platforms on frequency of purchasing per online shopping session. Using clickstream data from a multinational retailer, we find that device modality drives purchase frequency, likely due to the differential ease of use of PCs, tablets, and smartphones. In particular, frequency of completed orders is highest when information search and purchase completion are highly convenient, such as when shopping via tablet. We also determine that information search in the form of reading online product reviews has no effect on mobile platforms, while it does on other platforms. These findings contribute to information search theory, suggesting that information search increases purchase likelihood when it is goal directed, extensive, and easy to conduct. Thus, the broad role of digital advertising should be to make the information search process easier and more convenient for consumers to stimulate purchases. These findings help digital advertisers understand information search patterns across device modalities. Implications for digital advertisers on electronic commerce (e-commerce) platforms are offered.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.