Given the research interest on Big Data in Marketing, we present a literature analysis based text mining semi-automated approach with goal of identifying main trends this domain. In particular, focuses relevant terms and topics related five dimensions: Data, Geographic location authors’ affiliation (countries continents), Products, Sectors. A total 1560 articles published from 2010 to 2015 were scrutinized. The findings revealed that is bipartite between technological domains, publications...

Particle swarm is an optimization paradigm for real-valued functions, based on the social dynamics of group interaction. We propose its application to training neural networks. Comparative tests were carried out, classification and regression tasks.

Abstract This article presents three methods to forecast accurately the amount of traffic in TCP/IP based networks: a novel neural network ensemble approach and two important adapted time series (ARIMA Holt‐Winters). In order assess their accuracy, several experiments were held using real‐world data from large Internet service providers. addition, different scales (5 min, 1 h day) distinct forecasting lookaheads analysed. The with achieved best results for 5 min hourly data, while...

Learning from data is a very attractive alternative to "manually" learning. Therefore, in the last decade use of machine learning has spread rapidly throughout computer science and beyond. This approach, supported on advanced statistics analysis, usually known as Data Mining (DM) been applied successfully different knowledge domains. In present study, we show that DM can make great contribution solving complex problems civil engineering, namely field geotechnical engineering. Particularly,...

Currently, the quality of Indonesian national road network is inadequate due to several constraints, including overcapacity and overloaded trucks. The high deterioration rate infrastructure in developing countries along with major budgetary restrictions growth traffic have led an emerging need for improving perfo rmance highway maintenance system. However, number intervening factors their complex effects require advanced tools successfully solve this problem. learning capabilities Data...

This paper presents a benchmark of supervised Automated Machine Learning (AutoML) tools. Firstly, we analyze the characteristics eight recent open-source AutoML tools (Auto-Keras, Auto-PyTorch, Auto-Sklearn, AutoGluon, H2O AutoML, rminer, TPOT and TransmogrifAI) describe twelve popular OpenML datasets that were used in (divided into regression, binary multi-class classification tasks). Then, perform comparison study with hundreds computational experiments based on three scenarios: General...

Digital journalism has faced a dramatic change and media companies are challenged to use data science algorithms be more competitive in Big Data era. While this is relatively new area of study the landscape, machine learning artificial intelligence increased substantially over last few years. In particular, adoption models for personalization recommendation attracted attention several publishers. Following trend, paper presents research literature analysis on role Science (DS) Journalism...

There are several supervised learning Data Mining (DM) methods, such as Neural Networks (NN), Support Vector Machines (SVM) and ensembles, that often attain high quality predictions, although the obtained models difficult to interpret by humans. In this paper, we open these black box DM using a novel visualization approach is based on Sensitivity Analysis (SA) method. particular, propose Global SA (GSA), which extends applicability of previous methods (e.g. classification tasks), techniques...