The thesis analyzes the causal relationship between the cotton spot,and the tendency and impact of prices of futures markets in Xinjiang by using ADF test,co-integration analysis,Granger causality test and other econo...The thesis analyzes the causal relationship between the cotton spot,and the tendency and impact of prices of futures markets in Xinjiang by using ADF test,co-integration analysis,Granger causality test and other econometric methods in order to discuss the interacted relationship between futures market prices of cotton and spot market prices since the futures of cotton in Xinjiang go public.The results of empirical analysis show that the spot market prices of cotton and the futures market prices in Xinjiang fluctuate prominently in the short run and tend to counterpoise in the long run;the futures market of cotton plays the role of leading the spot market prices of cotton in Xinjiang,while the spot market prices of cotton in Xinjiang impacts little on the futures market prices.The corresponding countermeasures are put forward.The government should continuously perfect the construction of the futures market of cotton in Xinjiang,so as to exert the function of price discovery and the function of hedging,and promote the development of cotton industry in Xinjiang.展开更多
Estimating the price of a financial asset or any tradable product is a complex task that depends on the availability of a reasonable amount of data samples. In the Brazilian electricity market environment, where spot ...Estimating the price of a financial asset or any tradable product is a complex task that depends on the availability of a reasonable amount of data samples. In the Brazilian electricity market environment, where spot prices are centrally calculated by computational models, the projection of hourly energy prices at the spot market is essential for decision-making, and with the particularities of this sector, this task becomes even more complex due to the stochastic behavior of some variables, such as the inflow to hydroelectric power plants and the correlation between variables that affect electricity generation, traditional statistical techniques of time series forecasting present an additional complexity when one tries to project scenarios of spot prices on different time horizons. To address these complexities of traditional forecasting methods, this study presents a new approach based on Machine Learning methodology applied to the electricity spot prices forecasting process. The model’s Learning Base is obtained from public information provided by the Brazilian official computational models: NEWAVE, DECOMP, and DESSEM. The application of the methodology to real cases, using back-testing with actual information from the Brazilian electricity sector demonstrates that the research is promising, as the adherence of the projections with the realized values is significant.展开更多
基金Supported by The President Foundation Program of Tarim University(TDSKSS08002)
文摘The thesis analyzes the causal relationship between the cotton spot,and the tendency and impact of prices of futures markets in Xinjiang by using ADF test,co-integration analysis,Granger causality test and other econometric methods in order to discuss the interacted relationship between futures market prices of cotton and spot market prices since the futures of cotton in Xinjiang go public.The results of empirical analysis show that the spot market prices of cotton and the futures market prices in Xinjiang fluctuate prominently in the short run and tend to counterpoise in the long run;the futures market of cotton plays the role of leading the spot market prices of cotton in Xinjiang,while the spot market prices of cotton in Xinjiang impacts little on the futures market prices.The corresponding countermeasures are put forward.The government should continuously perfect the construction of the futures market of cotton in Xinjiang,so as to exert the function of price discovery and the function of hedging,and promote the development of cotton industry in Xinjiang.
文摘Estimating the price of a financial asset or any tradable product is a complex task that depends on the availability of a reasonable amount of data samples. In the Brazilian electricity market environment, where spot prices are centrally calculated by computational models, the projection of hourly energy prices at the spot market is essential for decision-making, and with the particularities of this sector, this task becomes even more complex due to the stochastic behavior of some variables, such as the inflow to hydroelectric power plants and the correlation between variables that affect electricity generation, traditional statistical techniques of time series forecasting present an additional complexity when one tries to project scenarios of spot prices on different time horizons. To address these complexities of traditional forecasting methods, this study presents a new approach based on Machine Learning methodology applied to the electricity spot prices forecasting process. The model’s Learning Base is obtained from public information provided by the Brazilian official computational models: NEWAVE, DECOMP, and DESSEM. The application of the methodology to real cases, using back-testing with actual information from the Brazilian electricity sector demonstrates that the research is promising, as the adherence of the projections with the realized values is significant.