Temporal mixture ensemble models for probabilistic forecasting of intraday cryptocurrency volume

AbstractWe study the problem of the intraday short-term volume forecasting in cryptocurrency multi-markets. The predictions are built by using transaction and order book data from different markets where the exchange takes place. Methodologically, we propose a temporal mixture ensemble, capable of adaptively exploiting, for the forecasting, different sources of data and providing a volume point estimate, as well as its uncertainty. We provide evidence of the clear outperformance of our model with respect to econometric models. Moreover our model performs slightly better than Gradient Boosting Machine while having a much clearer interpretability of the results. Finally, we show that the above results are robust also when restricting the prediction analysis to each volume quartile.

Download Full-text

Multistep-Ahead Solar Radiation Forecasting Scheme Based on the Light Gradient Boosting Machine: A Case Study of Jeju Island

Remote Sensing ◽

10.3390/rs12142271 ◽

2020 ◽

Vol 12 (14) ◽

pp. 2271 ◽

Cited By ~ 2

Author(s):

Jinwoong Park ◽

Jihoon Moon ◽

Seungmin Jung ◽

Eenjun Hwang

Keyword(s):

Solar Radiation ◽

Global Solar Radiation ◽

Jeju Island ◽

Gradient Boosting ◽

Probabilistic Forecasting ◽

Training Time ◽

Light Gradient ◽

Proposed Model ◽

Gradient Boosting Machine ◽

Time Problem

Smart islands have focused on renewable energy sources, such as solar and wind, to achieve energy self-sufficiency. Because solar photovoltaic (PV) power has the advantage of less noise and easier installation than wind power, it is more flexible in selecting a location for installation. A PV power system can be operated more efficiently by predicting the amount of global solar radiation for solar power generation. Thus far, most studies have addressed day-ahead probabilistic forecasting to predict global solar radiation. However, day-ahead probabilistic forecasting has limitations in responding quickly to sudden changes in the external environment. Although multistep-ahead (MSA) forecasting can be used for this purpose, traditional machine learning models are unsuitable because of the substantial training time. In this paper, we propose an accurate MSA global solar radiation forecasting model based on the light gradient boosting machine (LightGBM), which can handle the training-time problem and provide higher prediction performance compared to other boosting methods. To demonstrate the validity of the proposed model, we conducted a global solar radiation prediction for two regions on Jeju Island, the largest island in South Korea. The experiment results demonstrated that the proposed model can achieve better predictive performance than the tree-based ensemble and deep learning methods.

Download Full-text

Protein pKa prediction by tree-based machine learning

10.26434/chemrxiv-2021-4d420 ◽

2021 ◽

Author(s):

Ada Y. Chen ◽

Juyong Lee ◽

Ana Damjanovic ◽

Bernard R. Brooks

Keyword(s):

Machine Learning ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Pka Prediction ◽

Light Gradient ◽

Structure Database ◽

Gradient Boosting Machine ◽

Extreme Gradient Boosting ◽

Better Than ◽

Protein Pka

We present four tree-based machine learning models for protein pKa prediction. The four models, Random Forest, Extra Trees, eXtreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM), were trained on three experimental PDB and pKa datasets, two of which included a notable portion of internal residues. We observed similar performance among the four machine learning algorithms. The best model trained on the largest dataset performs 37% better than the widely used empirical pKa prediction tool PROPKA. The overall RMSE for this model is 0.69, with surface and buried RMSE values being 0.56 and 0.78, respectively, considering six residue types (Asp, Glu, His, Lys, Cys and Tyr), and 0.63 when considering Asp, Glu, His and Lys only. We provide pKa predictions for proteins in human proteome from the AlphaFold Protein Structure Database and observed that 1% of Asp/Glu/Lys residues have highly shifted pKa values close to the physiological pH.

Download Full-text

Novel Data-Driven Models Applied to Short-Term Electric Load Forecasting

Applied Sciences ◽

10.3390/app11125708 ◽

2021 ◽

Vol 11 (12) ◽

pp. 5708

Author(s):

Manuel Lopez-Martin ◽

Antonio Sanchez-Esguevillas ◽

Luis Hernandez-Callejo ◽

Juan Ignacio Arribas ◽

Belen Carro

Keyword(s):

Deep Learning ◽

Load Forecasting ◽

Data Driven ◽

Critical Parameters ◽

Gradient Boosting ◽

Dynamic Mode ◽

Electric Load ◽

Short Term ◽

Ensemble Models ◽

Electric Load Forecasting

This work brings together and applies a large representation of the most novel forecasting techniques, with origins and applications in other fields, to the short-term electric load forecasting problem. We present a comparison study between different classic machine learning and deep learning techniques and recent methods for data-driven analysis of dynamical models (dynamic mode decomposition) and deep learning ensemble models applied to short-term load forecasting. This work explores the influence of critical parameters when performing time-series forecasting, such as rolling window length, k-step ahead forecast length, and number/nature of features used to characterize the information used as predictors. The deep learning architectures considered include 1D/2D convolutional and recurrent neural networks and their combination, Seq2seq with and without attention mechanisms, and recent ensemble models based on gradient boosting principles. Three groups of models stand out from the rest according to the forecast scenario: (a) deep learning ensemble models for average results, (b) simple linear regression and Seq2seq models for very short-term forecasts, and (c) combinations of convolutional/recurrent models and deep learning ensemble models for longer-term forecasts.

Download Full-text

User behaviour analysis and churn prediction in ISP

New Trends and Issues Proceedings on Advances Pure and Applied Sciences ◽

10.18844/gjpaas.v0i12.4987 ◽

2020 ◽

pp. 57-67

Author(s):

Ahmet Turkmen ◽

Cenk Anil Bahcevan ◽

Youssef Alkhanafseh ◽

Esra Karabiyik

Keyword(s):

Machine Learning ◽

Service Sector ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Different Types ◽

Query Logs ◽

Boosting Algorithm ◽

Different Sources ◽

Better Than

There is no doubt that customer retention is vital for the service sector as companies’ revenue is significantly based on their customers’ financial returns. The prediction of customers who are at the risk of leaving a company’s services is not possible without using their connection details, support tickets and network traffic usage data. This paper demonstrates the importance of data mining and its outcome in the telecommunication area. The data in this paper are collected from different sources like Net Flow logs, call records and DNS query logs. These different types of data are aggregated together to decrease the missing information. Finally, machine learning algorithms are evaluated based on the customer dataset. The results of this study indicate that the gradient boosting algorithm performs better than other machine learning algorithms for this dataset. Keywords: Data analysis, customer satisfaction, subscriber churn, machine learning, telecommunication.

Download Full-text

Investigating the use of random forest, gradient boosting machine, support vector machine and their ensemble applied to fault detection

10.26678/abcm.cobem2017.cob17-1600 ◽

2017 ◽

Author(s):

Luis Felipe Nogoseke ◽

Gabriel Herman Bernardim Andrade ◽

Marco Boaretto ◽

Leandro Coelho

Keyword(s):

Support Vector Machine ◽

Random Forest ◽

Fault Detection ◽

Gradient Boosting ◽

Support Vector ◽

Gradient Boosting Machine

Download Full-text

Long-term Better Than Short-term ADT With Salvage RT

Case Medical Research ◽

10.31525/ct1-nct04242017 ◽

2020 ◽

Author(s):

Keyword(s):

Short Term ◽

Better Than

Download Full-text

An Ensemble Model for Short-Term Wind Power Forecasting using Deep Learning and Gradient Boosting Algorithms

2020 21st National Power Systems Conference (NPSC) ◽

10.1109/npsc49263.2020.9331902 ◽

2020 ◽

Author(s):

Devesh Kumar ◽

Rishabh Abhinav ◽

Naran Pindoriya

Keyword(s):

Deep Learning ◽

Wind Power ◽

Gradient Boosting ◽

Ensemble Model ◽

Short Term ◽

Wind Power Forecasting ◽

Boosting Algorithms ◽

Power Forecasting

Download Full-text

Estimation of modified expansive soil CBR with multivariate adaptive regression splines, random forest and gradient boosting machine

Innovative Infrastructure Solutions ◽

10.1007/s41062-021-00568-z ◽

2021 ◽

Vol 6 (4) ◽

Author(s):

Chijioke Christopher Ikeagwuani

Keyword(s):

Random Forest ◽

Expansive Soil ◽

Multivariate Adaptive Regression Splines ◽

Gradient Boosting ◽

Regression Splines ◽

Gradient Boosting Machine ◽

Adaptive Regression ◽

Adaptive Regression Splines

Download Full-text

A Multi-Class Automatic Sleep Staging Method Based on Photoplethysmography Signals

Entropy ◽

10.3390/e23010116 ◽

2021 ◽

Vol 23 (1) ◽

pp. 116

Author(s):

Xiangfa Zhao ◽

Guobing Sun

Keyword(s):

Time Domain ◽

Single Channel ◽

Kappa Statistic ◽

Gradient Boosting ◽

Sleep Staging ◽

Challenging Problem ◽

Sleep State ◽

Light Gradient ◽

Gradient Boosting Machine ◽

The Time Domain

Automatic sleep staging with only one channel is a challenging problem in sleep-related research. In this paper, a simple and efficient method named PPG-based multi-class automatic sleep staging (PMSS) is proposed using only a photoplethysmography (PPG) signal. Single-channel PPG data were obtained from four categories of subjects in the CAP sleep database. After the preprocessing of PPG data, feature extraction was performed from the time domain, frequency domain, and nonlinear domain, and a total of 21 features were extracted. Finally, the Light Gradient Boosting Machine (LightGBM) classifier was used for multi-class sleep staging. The accuracy of the multi-class automatic sleep staging was over 70%, and the Cohen’s kappa statistic k was over 0.6. This also showed that the PMSS method can also be applied to stage the sleep state for patients with sleep disorders.

Download Full-text