1,721,038 research outputs found
A profitable trading algorithm for cryptocurrencies using a Neural Network model
Full text linkAlgorithmic trading enables the execution of orders using a set of rules determined by a computer program. Orders are submitted based on an asset’s expected price in the future, an approach well suited for high-volatility markets, such as those trading in cryptocurrencies. The goal of this study is to find a reliable and profitable model to predict the future direction of a crypto asset’s price based on publicly available historical data. We first develop a novel labeling scheme and map this problem into a Machine Learning classification problem. The model is then validated on three major cryptocurrencies through an extensive backtest over a bull, bear and flat market. Finally, the contribution of each feature to the classification output is analyzed
Advanced statistical analysis of Local Bubble Size Distributions in 2D gas fluidized beds
No full textThe principal difficulty in analysing fluidization quality and bubble dynamics is related to the possibility of measuring or predicting the physical and geometrical properties of gas bubbles rising in a granular medium. Even the development of detailed experimental correlations gives poor results, being necessary a fully statistical approach. On the above basis, the present work focuses on the statistical analysis of the behaviour of a 2-D fluidized bed operating under bubbling and slugging conditions, performing measurements of Local Bubble Size Distributions (BSD) along the bed. The analysis allowed to observe a characteristic bimodal shape of BSDs for different particles dimension and fluidization velocities, due to the contemporary presence of random coalescence, splitting and nucleation phenomena. The presence of a characteristic peak of the distribution at small diameters accounts for the enhanced mixing effects due to small bubbles, while the second peak is related to large bubbles responsible for gas bypass. Conversely, an almost Gaussian distribution is obtained when a BSD weighed on bubble area is compute
CFD prediction of bubble behavior in two-dimensional gas-solid fluidized beds
No full textThis work focuses on the computational fluid dynamics (CFD) simulation of a laboratory-scale, two-dimensional fluidized bed and the relevant experiments in order to validate the prediction capability of the adopted codes and models. Both experimental and computational quantitative data were analyzed by means of an original digital image analysis technique, allowing for coherent comparison of computational and experimental results. In particular, this work analyzes the capability of the CFD simulations in predicting the fluctuating behavior of bubbling fluidized beds by means of frequency analysis of bubble-related phenomena
Lagrangian simulation of bubbling behaviour in gas fluidized beds and validation with experimental data
No full text
- …
