Large-Scale Sequential Learning for Recommender and Engineering Systems

TL;DR

This thesis introduces novel sequential learning algorithms for recommender and energy systems, demonstrating their effectiveness through empirical experiments showing improved accuracy and convergence speed.

Contribution

It presents SAROS, a new algorithm for personalized ranking in recommender systems, and a neighbor-aware fault detection method for power grids, both showing superior performance.

Findings

SAROS outperforms classical methods in convergence speed and accuracy.

Neighbor-based fault detection improves power grid fault localization.

Empirical results confirm the effectiveness of proposed algorithms.

Abstract

In this thesis, we focus on the design of an automatic algorithms that provide personalized ranking by adapting to the current conditions. To demonstrate the empirical efficiency of the proposed approaches we investigate their applications for decision making in recommender systems and energy systems domains. For the former, we propose novel algorithm called SAROS that take into account both kinds of feedback for learning over the sequence of interactions. The proposed approach consists in minimizing pairwise ranking loss over blocks constituted by a sequence of non-clicked items followed by the clicked one for each user. We also explore the influence of long memory on the accurateness of predictions. SAROS shows highly competitive and promising results based on quality metrics and also it turn out faster in terms of loss convergence than stochastic gradient descent and batch classical approaches. Regarding power systems, we propose an algorithm for faulted lines detection based on focusing of misclassifications in lines close to the true event location. The proposed idea of taking into account the neighbour lines shows statistically significant results in comparison with the initial approach based on convolutional neural networks for faults detection in power grid.