Blockchain is currently one of the most important topics in both the academia and industry world, mainly due to the possible effects that the continuing application of this new technology could have. The adoption of this technology by FinTech companies constitutes the next step towards the expansion of blockchain and its sustainability. The paper conducts a mapping study on the research topics, limitations, gaps and future trends of blockchain in FinTech companies. A total of 49 papers from a scientific database (Web of Science Core Collection) have been analyzed. The results show a deep focus in challenges such as security, scalability, legal and regulatory, privacy or latency, with proposed solutions still to be far from being effective. A vast majority of the research is focused into finance and banking sector, obviating other industries that could play a crucial role in the further expansion of blockchain. This study can contribute to researchers as a starting point for their investigation, as well as a source for recommendations on future investigation directions regarding blockchain in the FinTech sector.

The Open University's repository of research publications and other research outputs Applying machine learning to the dynamic selection of replenishment policies in fast-changing supply chain environments

The aim of this research is to examine the result of the application of the indicators Relative Strength Index (RSI), Moving Average Convergence Divergence (MACD), Momentum and Stochastic in different companies of the Spanish continuous market. By using these indicators, it is intended to give purchase and sale recommendations to small investors. The generation of great capital gains depends on the type of the stock exchange company and the indicator which is being used. In addition, this research solves the problems in case of ambiguity, in the indicators, for the traders.

A common way of dynamically scheduling jobs in a manufacturing system is by implementing dispatching rules. The issues with this method are that the performance of these rules depends on the state the system is in at each moment and also that no "ideal" single rule exists for all the possible states that the system may be in. Therefore, it would be interesting to use the most appropriate dispatching rule for each instance. To achieve this goal, a scheduling approach that uses machine learning can be used. Analyzing the previous performance of the system (training examples) by means of this technique, knowledge is obtained that can be used to decide which is the most appropriate dispatching rule at each moment in time. In this paper, a literature review of the main machine learning based scheduling approaches from the last decade is presented.

In this paper, two different Locally Weighted Support Vector Regression (wSVR) algorithms are generated and applied to the task of forecasting and trading five European Exchange Traded Funds. The trading application covers the recent European Monetary Union debt crisis. The performance of the proposed models is benchmarked against traditional Support Vector Regression (SVR) models. The Radial Basis Function, the Wavelet and the Mahalanobis kernel are explored and tested as SVR kernels. Finally, a novel statistical SVR input selection procedure is introduced based on a principal component analysis and the Hansen et al. (2011) model confidence test. The results demonstrate the superiority of the wSVR models over the traditional SVRs and of the v-SVR over the ε-SVR algorithms. We note that the performance of all models varies and considerably deteriorates in the peak of the debt crisis. In terms of the kernels, our results do not confirm the belief that the Radial Basis Function is the optimum choice for financial series.

The aim of this research was to analyse the different results that can be achieved using support vector machines (SVM) to forecast the weekly change movement of different simulated markets. The markets are developed by a GARCH model based on the S&P 500. These simulated markets are grouped by a main parameter: high volatility, bearish trend, bullish trend and low volatility. The inputs retained of the SVM are traditional technical trading rules used in quantitative analysis, such as relative strength index (RSI) and moving average convergence divergence (MACD) decision rules. The outputs of the SVM are the degree of set membership and market movement (bullish or bearish). The design of the SVM algorithm has been developed by Matlab and SVM‐KM. The configuration for the SVM shows that the best results are achieved in simulated markets with high volatility; also results are good in trend simulated markets. Copyright © 2014 John Wiley & Sons, Ltd.

No abstract

In this study, we generate 50 Multi-Layer Perceptons, 50 Radial Basis Functions, 50 Higher Order Neural Networks and 50 Recurrent Neural Network and we explore their utility in forecasting and trading the DJIA, NASDAQ 100 and the NIKKEI 225 stock indices. The statistical significance of the forecasts is examined through the False Discovery Ratio of Bajgrowicz and Scaillet (2012). Two financial leverages, based on the levels of financial stress and the financial volatility respectively, are also applied. In terms of the results, we note that RNN have the higher percentage of significant models and present the stronger profitability compared to their Neural Network counterparts. The financial leverages doubles the trading performance of our models.