Understanding Time Series Forecasting Using Deep Learning
Deep learning for time series forecasting involves training models to predict future values based on historical data patterns. This method is used in various applications, such as sales forecasting and disease prediction, to make informed decisions and plan ahead effectively.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
Time Series Forecasting Using Deep Learning BY BREHIMA KONE
1-Forecasting the values of future time steps of sequence by train a sequence to sequence regression LSTM network, where the responses are the training sequences with values shifted by one-time step. Forecast Time Series data using a long short-term memory (LSTM) network 2-Forecasting the values of multiple time step 3-Applying the deep learning -based time series prediction on some applications, such as chickenpox prediction.
Deep learning is currently an extremely active research area in machine learning and pattern recognition society. Deep learning refers to machine techniques For example, companies like Google , Apple , and Facebook, who collect and analyze massive amounts of data everyday What is deep learning
Why time series forecasting Example, the most common, basic example of a time series is seasonal sales revenues. Many companies are exploring time series forecasting as a way of making better business decisions. Time series forecasting is the use of statistical methods to predict future behavior based on historical data. Time series is looking at data overtime to forecast or predict what will happen in the next time period.
Time Series Data A time series is a sequence of data points through time. Thus, when dealing with time series data, order matters. -Data is measured sequentially and equally space in time. Time series data have two important properties: -Each time unit has at most one measurement.
Time Series Patterns Most time series data usually have at least one of these three kinds of patterns: Trend Seasonality Cycle
Trend Figure1 The general behavior of a time serie
Seasonality A season pattern is any kind of fluctuation(change ) in a time series that caused by calendar-related events. Seasonality always has fixed frequencies. A seasonal pattern always starts and end in the same period of a week, year,etc.
Load Chickenpox dataset contains a single time series, with time steps corresponding to months and values corresponding to the number of cases. The output is a cell array, where each element is a single time step. Sequence Data
Conclusion Time series forecasting is an important area of machine learning that is often neglected. It is important because there are so many prediction problems that involve a time component. These problems are neglected because it is time component that makes time series problems more difficult to handle.
Acknowledgement Acknowledgement The fellow would like to thank the mentor, Dr. Nian Zhang for her supervision and continuous support, Lockheed Martin for funding the research fellowship program, and the school of Engineering and Applied science (SEAS) of the university of the District of Columbia for arranging the fellowship and selecting the fellow.
