{"title":"风险交易策略:基于ARIMA和迭代风险交易模型的交易策略系统","authors":"J. Song, Henghao Cheng, Haolin Liu","doi":"10.1145/3537693.3537728","DOIUrl":null,"url":null,"abstract":"Market transactions are of great significance to the development of the financial field. Gold and bitcoin, as very important financial investment products, often contain a series of operation laws. They can bring great benefits to investors, but they may also bring immeasurable economic losses due to investors' improper decision-making. This paper constructs a series of models in order to obtain the best investment strategy. Firstly, two ARIMA models are constructed, that is, using the historical time price data of gold and bitcoin to predict the price of gold and bitcoin in the next trading day. Apriori algorithm is used to find frequent sets and determine the initial allocation ratio of gold to bitcoin. Then, the predicted data are iteratively analyzed to obtain the transaction decision-making scheme. As the transaction is limited by commission and trading day, the established model follows the following principles: 1) the profit on that day is greater than the Commission to be paid. 2) The trading volume of the day should be less than the total amount currently held. It can be divided into two cases: Gold opening and gold closing. The trading decision scheme is calculated through iteration. Through sensitivity analysis, it is found that the change of commission value does not affect the trend of investment income, but with the increase of commission value, the income decreases, the Commission value decreases and the income increases.","PeriodicalId":71902,"journal":{"name":"电子政务","volume":"1 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2022-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Risk Trading Strategy: A Trading Strategy System Based on ARIMA and Iterative Risk Trading Model\",\"authors\":\"J. Song, Henghao Cheng, Haolin Liu\",\"doi\":\"10.1145/3537693.3537728\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Market transactions are of great significance to the development of the financial field. Gold and bitcoin, as very important financial investment products, often contain a series of operation laws. They can bring great benefits to investors, but they may also bring immeasurable economic losses due to investors' improper decision-making. This paper constructs a series of models in order to obtain the best investment strategy. Firstly, two ARIMA models are constructed, that is, using the historical time price data of gold and bitcoin to predict the price of gold and bitcoin in the next trading day. Apriori algorithm is used to find frequent sets and determine the initial allocation ratio of gold to bitcoin. Then, the predicted data are iteratively analyzed to obtain the transaction decision-making scheme. As the transaction is limited by commission and trading day, the established model follows the following principles: 1) the profit on that day is greater than the Commission to be paid. 2) The trading volume of the day should be less than the total amount currently held. It can be divided into two cases: Gold opening and gold closing. The trading decision scheme is calculated through iteration. Through sensitivity analysis, it is found that the change of commission value does not affect the trend of investment income, but with the increase of commission value, the income decreases, the Commission value decreases and the income increases.\",\"PeriodicalId\":71902,\"journal\":{\"name\":\"电子政务\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-04-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"电子政务\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://doi.org/10.1145/3537693.3537728\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"电子政务","FirstCategoryId":"96","ListUrlMain":"https://doi.org/10.1145/3537693.3537728","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Risk Trading Strategy: A Trading Strategy System Based on ARIMA and Iterative Risk Trading Model
Market transactions are of great significance to the development of the financial field. Gold and bitcoin, as very important financial investment products, often contain a series of operation laws. They can bring great benefits to investors, but they may also bring immeasurable economic losses due to investors' improper decision-making. This paper constructs a series of models in order to obtain the best investment strategy. Firstly, two ARIMA models are constructed, that is, using the historical time price data of gold and bitcoin to predict the price of gold and bitcoin in the next trading day. Apriori algorithm is used to find frequent sets and determine the initial allocation ratio of gold to bitcoin. Then, the predicted data are iteratively analyzed to obtain the transaction decision-making scheme. As the transaction is limited by commission and trading day, the established model follows the following principles: 1) the profit on that day is greater than the Commission to be paid. 2) The trading volume of the day should be less than the total amount currently held. It can be divided into two cases: Gold opening and gold closing. The trading decision scheme is calculated through iteration. Through sensitivity analysis, it is found that the change of commission value does not affect the trend of investment income, but with the increase of commission value, the income decreases, the Commission value decreases and the income increases.