Branding/Logomark minus Citation Combined Shape Icon/Bookmark-empty Icon/Copy Icon/Collection Icon/Close Copy 7 no author result Created with Sketch. Icon/Back Created with Sketch. Match!

A novel cryptocurrency price trend forecasting model based on LightGBM

Published on Dec 1, 2018in Finance Research Letters 1.71
· DOI :10.1016/j.frl.2018.12.032
Xiaolei Sun11
Estimated H-index: 11
(CAS: Chinese Academy of Sciences),
Mingxi Liu1
Estimated H-index: 1
(CAS: Chinese Academy of Sciences),
Zeqian Sima1
Estimated H-index: 1
Cite
Abstract
Abstract Forecasting cryptocurrency prices is crucial for investors. In this paper, we adopt a novel Gradient Boosting Decision Tree (GBDT) algorithm, Light Gradient Boosting Machine (LightGBM), to forecast the price trend (falling, or not falling) of cryptocurrency market. In order to utilize market information, we combine the daily data of 42 kinds of primary cryptocurrencies with key economic indicators. Results show that the robustness of the LightGBM model is better than the other methods, and the comprehensive strength of the cryptocurrencies impacts the forecasting performance. This can effectively guide investors in constructing an appropriate cryptocurrency portfolio and mitigate risks.
  • References (13)
  • Citations (1)
Cite
References13
Newest
Published on Mar 1, 2018in International Review of Financial Analysis 1.69
Khaled Guesmi14
Estimated H-index: 14
,
Khaled Guesmi + 1 AuthorsZied Ftiti11
Estimated H-index: 11
Abstract The paper investigates the proprieties of Bitcoin in the financial markets. Specifically, we explore the conditional cross effects and volatility spillover between Bitcoin and financial indicators using different multivariate GARCH specifications. The nature of interaction between Bitcoin and financial variables and their transmission mechanisms are taken into account when analyzing the diversification and hedging effectiveness across gold asset and stock market. Our findings suggest th...
Qiang Ji21
Estimated H-index: 21
(CAS: Chinese Academy of Sciences),
Bouri Elie16
Estimated H-index: 16
(Holy Spirit University of Kaslik)
+ 1 AuthorsDavid Roubaud16
Estimated H-index: 16
Unlike prior studies that have mostly relied on ad hoc network structures, we use a data-driven methodology, namely the directed acyclic graph (DAG), to uncover the contemporaneous and lagged causal relations among Bitcoin and a set of financial assets. The DAG methodology allows the identification of networks of causality based on the observed correlations and partial correlations approach, without making a priori causal assumptions. The main results indicate that the Bitcoin market is quite is...
Published on Aug 1, 2018in Energy Economics 4.15
Refk Selmi9
Estimated H-index: 9
,
Walid Mensi14
Estimated H-index: 14
(Sultan Qaboos University)
+ 1 AuthorsJamal Bouoiyour12
Estimated H-index: 12
This study assesses the roles of Bitcoin as a hedge, a safe haven and/or a diversifier against extreme oil price movements, in comparison to the corresponding roles of gold. We use a quantile-on-quantile regression approach to capture the dependence structure between the considered market returns under different Bitcoin market conditions, while considering nuances of oil price movements, compared to gold. Our findings show that both Bitcoin and gold would serve the roles of a hedge, a safe haven...
Published on Jan 1, 2018in Finance Research Letters 1.71
Ender Demir7
Estimated H-index: 7
(Istanbul Medeniyet University),
Giray Gozgor10
Estimated H-index: 10
(Istanbul Medeniyet University)
+ 1 AuthorsSamuel A. Vigne6
Estimated H-index: 6
('QUB': Queen's University Belfast)
This paper analyzes the prediction power of the economic policy uncertainty (EPU) index on the daily Bitcoin returns. Using the Bayesian Graphical Structural Vector Autoregressive model as well as the Ordinary Least Squares and the Quantile-on-Quantile Regression estimations, the paper finds that the EPU has a predictive power on Bitcoin returns. Fundamentally, Bitcoin returns are negatively associated with the EPU. However, the effect is positive and significant at both lower and higher quantil...
Published on Dec 4, 2017 in NeurIPS (Neural Information Processing Systems)
Guolin Ke2
Estimated H-index: 2
(Microsoft),
Qi Meng5
Estimated H-index: 5
(PKU: Peking University)
+ 5 AuthorsTie-Yan Liu40
Estimated H-index: 40
(Microsoft)
Gradient Boosting Decision Tree (GBDT) is a popular machine learning algorithm, and has quite a few effective implementations such as XGBoost and pGBRT. Although many engineering optimizations have been adopted in these implementations, the efficiency and scalability are still unsatisfactory when the feature dimension is high and data size is large. A major reason is that for each feature, they need to scan all the data instances to estimate the information gain of all possible split points, whi...
Published on Dec 1, 2017in Finance Research Letters 1.71
Yonghong Jiang1
Estimated H-index: 1
(UW: University of Wisconsin-Madison),
He Nie1
Estimated H-index: 1
(JNU: Jinan University),
Weihua Ruan1
Estimated H-index: 1
(JNU: Jinan University)
This study attempts to investigate the time-varying long-term memory in the Bitcoin market through a rolling window approach and by employing a new efficiency index (Sensoy and Hacihasanoglu, 2014). The daily dataset for the period from 2010 to 2017 is utilized, and some interesting findings emerge that: (i) all of the generalized Hurst exponents in the Bitcoin market are above 0.5; (ii) long-term memory exists in the Bitcoin market; (iii) high degree of inefficiency ratio; (iv) the Bitcoin mark...
Published on Nov 1, 2017in Finance Research Letters 1.71
Bouri Elie16
Estimated H-index: 16
(Holy Spirit University of Kaslik),
Rangan Gupta29
Estimated H-index: 29
(University of Pretoria)
+ 1 AuthorsDavid Roubaud16
Estimated H-index: 16
We examine whether Bitcoin can hedge global uncertainty, measured by the first principal component of the VIXs of 14 developed and developing equity markets. After decomposing Bitcoin returns into various frequencies, i.e., investment horizons, and given evidence of heavy-tails, we employ quantile regression. We reveal that Bitcoin does act as a hedge against uncertainty: it reacts positively to uncertainty at both higher quantiles and shorter frequency movements of Bitcoin returns. Further, we ...
Published on Mar 1, 2016in IEEE Transactions on Mobile Computing 4.47
Yishuang Geng20
Estimated H-index: 20
(WPI: Worcester Polytechnic Institute),
Jin Chen1
Estimated H-index: 1
(Skyworks Solutions)
+ 2 AuthorsKaveh Pahlavan45
Estimated H-index: 45
(WPI: Worcester Polytechnic Institute)
The real-time health monitoring system is a promising body area network application to enhance the safety of firefighters when they are working in harsh and dangerous environments. Other than monitoring the physiological status of the firefighters, on-body monitoring networks can be also regarded as a candidate solution of motion detection and classification. In this paper, we consider motion classification with features obtained from the on-body radio frequency (RF) channel. Various relevant RF...
Published on Jan 1, 2015in IEEE Transactions on Instrumentation and Measurement 3.07
Abdenour Soualhi5
Estimated H-index: 5
,
Kamal Medjaher9
Estimated H-index: 9
,
Noureddine Zerhouni27
Estimated H-index: 27
The detection, diagnostic, and prognostic of bearing degradation play a key role in increasing the reliability and safety of electrical machines, especially in key industrial sectors. This paper presents a new approach that combines the Hilbert-Huang transform (HHT), the support vector machine (SVM), and the support vector regression (SVR) for the monitoring of ball bearings. The proposed approach uses the HHT to extract new heath indicators from stationary/nonstationary vibration signals able t...
Published on May 1, 2009in Expert Systems With Applications 4.29
M. Arun Kumar6
Estimated H-index: 6
(IITD: Indian Institute of Technology Delhi),
Madan Gopal15
Estimated H-index: 15
(IITD: Indian Institute of Technology Delhi)
In this paper we formulate a least squares version of the recently proposed twin support vector machine (TSVM) for binary classification. This formulation leads to extremely simple and fast algorithm for generating binary classifiers based on two non-parallel hyperplanes. Here we attempt to solve two modified primal problems of TSVM, instead of two dual problems usually solved. We show that the solution of the two modified primal problems reduces to solving just two systems of linear equations a...
Cited By1
Newest
Jing Zhou (Cardiff University), Wei Li (Hefei University of Technology)+ -3 AuthorsChengyi Xia27
Estimated H-index: 27
(Tianjin University of Technology)
Abstract In recent years, a new Internet-based unsecured credit model, peer-to-peer (P2P) lending, is flourishing and has become a successful complement to the traditional credit business. However, credit risk remains inevitable. A key challenge is creating a default prediction model that can effectively and accurately predict the default probability of each loan for a P2P lending platform. Due to the characteristics of P2P lending credit data, such as high dimension and class imbalance, convent...
Published on Sep 1, 2019in Chaos Solitons & Fractals 3.06
Aytac Altan1
Estimated H-index: 1
(Zonguldak Karaelmas University),
Seckin Karasu2
Estimated H-index: 2
(Zonguldak Karaelmas University),
Stelios Bekiros1
Estimated H-index: 1
(WLU: Wilfrid Laurier University)
Abstract The price forecasting of the digital currencies in the financial market is of great importance, especially after the recent global economic crises. Due to the nonlinear dynamics, which is including inherent fractality and chaoticity of the digital currencies, it is understood from the research conducted by many researchers that a single model is not sufficient in forecasting the digital currencies with very high accuracy. Since the single models used in the forecasting of digital curren...
Eduardo Sánchez (UCLM: University of Castilla–La Mancha), José Angel Olivas Varela11
Estimated H-index: 11
(UCLM: University of Castilla–La Mancha),
Francisco P. Romero12
Estimated H-index: 12
(UCLM: University of Castilla–La Mancha)
The cryptocurrencies are a new paradigm of transferring money between users. Their anonymous and non-centralized is a subject of debate around the globe that paired with the massive spikes and declines in value that are inherit to an unregistered asset. These facts make difficult for the common daily use of the cryptocurrencies as an exchange currency as instead they are being used as a new way to invest. What we propose in this article is a system for the better understanding of the cryptocurre...
Published on May 21, 2019in arXiv: Statistical Finance
Reaz Chowdhury (North South University), M. Arifur Rahman + 1 AuthorsM.R.C. Mahdy1
Estimated H-index: 1
At present, cryptocurrencies have become a global phenomenon in financial sectors as it is one of the most traded financial instruments worldwide. Cryptocurrency is not only one of the most complicated and abstruse fields among financial instruments, but it is also deemed as a perplexing problem in finance due to its high volatility. This paper makes an attempt to apply machine learning techniques on the index and constituents of cryptocurrency with a goal to predict and forecast prices thereof....