'Time is Money' : Deep Learning for Time Series Forecasting in Python
pganesh (~pganeshGapps) |
Whenever we have to make a decision under uncertainty, we all make our own forecasts. Even if we are not thinking that we are forecasting, our choices will be decided by our anticipation of results of our actions. Delays and indecision are the main reasons of failure. As a result of realizing 'Time is Money', 'Time Series Forecasting' is being applied in dynamic decision making problems. Time Series Analysis & Forecasting has been used by a wide range of businesses from managerial decisions, stock market analysis, sales, policy research, weather forecasting to astronomy. Deep learning may not be the best solution for all time series forecasting problems, but for those problems where classical methods fail and machine learning methods require elaborate feature engineering, deep learning methods can be used with great success.
Deep learning methods can offer lots of promises for time series forecasting. For example, deep learning methods such as Multilayer Perceptrons, Convolutional Neural Networks, and LSTM networks can handle temporal structures like trends and seasonality automatically. Besides, these can be used for automatic learning of temporal dependence of challenging time series forecasting problems.
Outcomes: (What you will get from this)
- Foundations: Introduction to the promise of deep learning methods for time series forecasting, data preparation for supervised learning, performance tuning in general
- Deep Learning Modelling: How to develop MLPs, CNNs & LSTMs for time series forecasting problems
- Univariate & Multivariate Forecasting: a methodical approach to univariate & multivariate time series forecasting
- Single-step & Multi-step Forecasting: working through a challenging multi-step time series forecasting problem
- You know your way around Basic Python Programming
- High level knowledge about how neural networks work
- Basic mathematics
- Github repository will be made public post-event
- Working as 'Associate Lead, Data Sciences' in an MNC fintech from last ~1.5 years.
- Implemented NLP solutions which give processes ~1mn financial transactions daily.
- Worked in Seattle based startup as a Full Stack Developer, deployed multiple microservices to production
- B.Tech.(CSE, IIT Jodhpur)
- Working as a Big Data Engineer in one of the large e-commerce MNC from last ~1.5 year.
- Developed scalable big data solutions & platforms for e-commerce MNC
- B.Tech.(ECE, IIT Roorkee)