Scholarlink

One of the core concepts in data science is time series forecasting, which is necessary to understand and forecast how different events will unfold. This paper aims to forecast time series data relevant to three crucial domains: COVID-19 instances, crude oil stock prices, and weather perceptions. The collection provides complete historical records showing the evolution of COVID-19 instances, variations in crude oil stock prices, and diverse meteorological conditions. Employing advanced forecasting techniques, namely Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM), and Autoregressive Integrated Moving Average (ARIMA), this research endeavors to provide accurate predictions for future trends in these interconnected phenomena. By using these forecasting approaches, the study intends to give insights into the probable trajectories of COVID-19 spread, crude oil market dynamics, and weather patterns. Such predictive insights hold significant implications for decision-making processes across diverse sectors, including public health, energy markets, and meteorology, thereby facilitating proactive measures and informed strategies to address emerging challenges and capitalize on emerging opportunities.

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

Predictive Analytics for Time Series Data: Leveraging Supervised Learning Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Vaibhav Bhogade,
  • B. Nithya

摘要

One of the core concepts in data science is time series forecasting, which is necessary to understand and forecast how different events will unfold. This paper aims to forecast time series data relevant to three crucial domains: COVID-19 instances, crude oil stock prices, and weather perceptions. The collection provides complete historical records showing the evolution of COVID-19 instances, variations in crude oil stock prices, and diverse meteorological conditions. Employing advanced forecasting techniques, namely Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM), and Autoregressive Integrated Moving Average (ARIMA), this research endeavors to provide accurate predictions for future trends in these interconnected phenomena. By using these forecasting approaches, the study intends to give insights into the probable trajectories of COVID-19 spread, crude oil market dynamics, and weather patterns. Such predictive insights hold significant implications for decision-making processes across diverse sectors, including public health, energy markets, and meteorology, thereby facilitating proactive measures and informed strategies to address emerging challenges and capitalize on emerging opportunities.