Scholarlink

This paper proposes nowcasting of high-frequency financial datasets in real-time with a 5-min interval using the streaming analytics feature of Apache Spark. The proposed 2-stage method consists of modelling chaos in the first stage followed by using a sliding window approach for separately training Lasso Regression (LR), Ridge Regression (RR), Generalized Linear Model (GLM), Gradient Boosting Tree (GBT) and Random Forest (RF) available in the MLLib library of Apache Spark in the second stage. The effectiveness of the proposed methodology is demonstrated on National Stock Exchange (NSE) dataset, Bombay Stock Exchange (BSE) dataset, and Bitcoin-INR conversion dataset. For evaluating the proposed methodology, we used measures such as Symmetric Mean Absolute Percentage Error (SMAPE), Directional Symmetry (DS) and Theil’s U Coefficient. We tested the statistical significance of the performance of the models using the Diebold Mariano (DM) test.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Nowcasting the Financial Time Series with Streaming Data Analytics Under Apache Spark

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mohammad Arafat Ali Khan,
  • Chandra Bhushan,
  • Vadlamani Ravi,
  • Vangala Sarveswara Rao,
  • Shiva Shankar Orsu

摘要

This paper proposes nowcasting of high-frequency financial datasets in real-time with a 5-min interval using the streaming analytics feature of Apache Spark. The proposed 2-stage method consists of modelling chaos in the first stage followed by using a sliding window approach for separately training Lasso Regression (LR), Ridge Regression (RR), Generalized Linear Model (GLM), Gradient Boosting Tree (GBT) and Random Forest (RF) available in the MLLib library of Apache Spark in the second stage. The effectiveness of the proposed methodology is demonstrated on National Stock Exchange (NSE) dataset, Bombay Stock Exchange (BSE) dataset, and Bitcoin-INR conversion dataset. For evaluating the proposed methodology, we used measures such as Symmetric Mean Absolute Percentage Error (SMAPE), Directional Symmetry (DS) and Theil’s U Coefficient. We tested the statistical significance of the performance of the models using the Diebold Mariano (DM) test.