Stock price prediction is a popular yet challenging task and deep learning provides the means to conduct the mining for the different patterns that trigger its dynamic movement. In this paper, the task is to predict the close price for 25 companies enlisted at the Bucharest Stock Exchange, from a novel data set introduced herein. Towards this scope, two traditional deep learning architectures are designed in comparison: a long short-memory network and a temporal convolutional neural model. Based on their predictions, a trading strategy, whose decision to buy or sell depends on two different thresholds, is proposed. A hill climbing approach selects the optimal values for these parameters. The prediction of the two deep learning representatives used in the subsequent trading strategy leads to distinct facets of gain.

Feature selection methods, as a preprocessing step to machine learning, is effective in reducing dimensionality, removing irrelevant data, increasing learning accuracy, and improving result comprehensibility. However, the recent increase of dimensionality of data poses a severe challenge to many existing feature selection methods with respect to efficiency and effectiveness. In this work, a novel concepts of relevant feature selection based on information gathered from decision rule and decision tree models were introduced. A new measures DRQualityImp and DTLevelImp were additionally defined. The first one is based on feature presence frequency and rule quality, while the second is based on feature presence on different levels inside decision tree. The efficiency and effectiveness of that method is demonstrated through the exemplary use of five real-world datasets. Promising initial results of classification efficiency could be gained together with substantial reduction of problem dimensionality.

Transcriptional regulation in multi-cellular organisms is a complex process involving multiple modular regulatory elements for each gene. Building whole-genome models of transcriptional networks requires mapping all relevant enhancers and then linking them to target genes. Previous methods of enhancer identification based either on sequence information or on epigenetic marks have different limitations stemming from incompleteness of each of these datasets taken separately.