Risk measurement in Bitcoin market by fusing LSTM with the joint-regression-combined forecasting model

PurposeThe purpose of the paper is to better measure the risks and volatility of the Bitcoin market by using the proposed novel risk measurement model.Design/methodology/approachThe joint regression analysis of value at risk (VaR) and expected shortfall (ES) can effectively overcome the non-elicitability problem of ES to better measure the risks and volatility of financial markets. And because of the incomparable advantages of the long- and short-term memory (LSTM) model in processing non-linear time series, the paper embeds LSTM into the joint regression combined forecasting framework of VaR and ES, constructs a joint regression combined forecasting model based on LSTM for jointly measuring VaR and ES, i.e. the LSTM-joint-combined (LSTM-J-C) model, and uses it to investigate the risks of the Bitcoin market.FindingsEmpirical results show that the proposed LSTM-J-C model can improve forecasting performance of VaR and ES in the Bitcoin market more effectively compared with the historical simulation, the GARCH model and the joint regression combined forecasting model.Social implicationsThe proposed LSTM-J-C model can provide theoretical support and practical guidance to cryptocurrency market investors, policy makers and regulatory agencies for measuring and controlling cryptocurrency market risks.Originality/valueA novel risk measurement model, namely LSTM-J-C model, is proposed to jointly estimate VaR and ES of Bitcoin. On the other hand, the proposed LSTM-J-C model provides risk managers more accurate forecasts of volatility in the Bitcoin market.

Phenotypic stability studies in pearl millet [Pennisetum glaucum (L.) R.Br.]

Genotype x environment interaction in pearl millet [Pennisetum glaucum (L.) R.Br.] was studied for grain yield by growing 57 genotypes consisting of 54 hybrids along with three standard checks in RBD with three replications under three different environments created by different irrigation numbers (E1, E2 and E3) with recommended dose of fertilizers during Kharif, 2015 at Agriculture Research Station farm, ARS Beechhwal, Bikaner. The nature and extent of genotype (g) x environment (e) interactions were studied. The joint regression analysis indicated the importance of unpredictable components along with predictable components of G x E interaction. Among the crosses RMS 6A x BIB-27 and ICMA 04999 x BIB-15 had higher grain yield per plant and showed stability for better management conditions and poor management conditions, respectively.

Growth response of European larch (Larix decidua Mill.) populations to climatic transfer A Novel Approach for Controlled Pollination in Casuarina equisetifolia

The study focuses on growth responses of Larix decidua provenances to climatic transfer based on a regional provenance experiment. This comprises a series of 5 trial plots situated in Germany and Slovakia, where 12 indigenous Sudetic and West-Carpathian larch provenances are planted. Transfer rates were defined as differences in altitudes or climatic variables between the site of plantation and the site of origin. 1st and 2nd-order polynomial regressions were used for the identification of overall trends of growth performance and responses to transfer. Sudetic provenances clearly outperformed the Carpathian ones on all test sites. When all provenances were considered jointly, height and breast-height diameter mostly showed significant monotonous geographical and climatic trends: the performance generally decreased with increasing altitude and precipitations and decreasing temperatures. The relationships between growth response and transfer rates (ecodistances) were mostly linear. However, when Sudetic and Carpathian provenances were considered separately, most significant response curves were unimodal. There is a very good correspondence between the responses in height and diameter growth within geographic groups, but the responses are not consistent between groups. Joint regression analysis showed that most provenances exhibited average stability. Stability indices are quite consistent between the response traits and did not show any association with the geographical position, climate of origin, or growth performance. The results indicate that populations in different climates remain adapted to a common optimum, the extent of local adaptation is quite limited. Possible explanations of this observation are briefly discussed.

Genotype by environment interaction and yield stability analysis of quality protein maize genotypes in Terai Region of Nepal

Grain yield stability for the new maize genotypes is an important target in maize breeding programs. The main objective of this study was to identify stable high yielding quality protein maize (QPM) genotypes under various locations and years in terai region of Nepal. Six quality protein maize genotypes along with Poshilo Makai-1 (Standard Check) and Farmer’s Variety (Local Check) were tested at three different locations namely Ayodhyapuri-2, Devendrapur, Madi, Chitwan; Rajahar-8, Bartandi, Rajahar, Nawalparasi; Mangalpur-2, Rampur, Chitwan during 2011 and 2012 spring and winter seasons under rainfed condition. The experiment was conducted using Randomized Complete Block Design with two replications in farmer’s fields. There was considerable variation among genotypes and environments for grain yield. The analysis of variance showed that mean squares of environments (E) was highly significant and genotypes (G) and genotype x environment interaction (GEI) were non significant. The genotypes S03TLYQ-AB02 and RampurS03FQ02 respectively produced the higher mean grain yield 5422±564 kg/ha and 5274±603 kg/ha across the locations. Joint regression analysis showed that RampurS03FQ02 and S03TLYQ-AB02 with regression coefficient 1.10 and 1.22 respectively are the most stable genotypes over the tested environments. The coefficient of determination (R2) for genotypes Rampur S03FQ02 and S03TLYQ-AB02 were as high as 0.954, confirming their high predictability to stability. Further confirmation from GGE biplot analysis showed that maize genotype S03TLYQ-AB02 followed by Rampur S03FQ02 were more stable and adaptive genotypes across the tested environments. Thus these genotypes could be recommended to farmers for general cultivation.DOI: http://dx.doi.org/10.3126/ijasbt.v1i2.8202 Int J Appl Sci Biotechnol, Vol. 1(2): 75-79