Financial Analytics with time series modelling and neural networks

Apply Online

The field of financial econometrics using advanced tools and techniques has emerged over the last decade. The intention of this course is to help practitioners cut through the vast literature on financial time series models, focusing on the most important and useful empirical concepts. This course is expected to develop a sound background in quantitative analysis of financial time series. It also aims to develop sound understanding in sequential data analysis by building a Long Short-term memory model (LSTM) of Neural Network. It offers a guide to analyse and model time series properties of financial data using machine learning approach through Python. The course is designed for researchers and practitioners in the finance industry. Our aim is to provide a road map from academic prospective to the research issues that are important for researchers and practitioners.

This short course aims to discuss a broader aspect of time series modeling on financial data with advanced tools and techniques. It covers applied econometric tools relating to univariate financial time series models and LSTM using Python. The course aims to develop insights of financial models with univariate time series analysis and neural networks models using stock market indices.

1. Fundamentals of Financial Time series a. Visualization of Time series data b. Autocorrelation functions and testing of stationarity of financial data c. Moving averages and time series smoothers 2. Univariate Time series modeling a. Introduction to ARIMA b. Building ARIMA model and forecasting market returns c. Modeling using ARIMAX 3. Modeling return volatility a. Autoregressive Conditional Heteroskedasticity (ARCH) modeling of market return. b. Generalized Autoregressive Conditional Heteroskedasticity (GARCH) modeling of market return. 4. Understanding Financial Time Series and Neural network a. Understanding Neural network b. AI Neural Network in financial Data c. Recurrence Neural Network (RNN) and its advantage and disadvantage d. Long Short-term Memory Model (LSTM)

Researchers, Academicians and Industry professionals

Course Details

Venue Online
Duration 18 Hrs.
Starts On Oct 21, 2022
Faculty Prof. Ajaya Kumar Panda

Fees Details

Duration Professional Fee*(Per participant) GST(18%) Total Fees(Per Participant) Programme Code
18 Hrs. 9,000.00 1,620.00 10,620.00 1 23 3 28
Apply Online

Download Brochure

*
*
*
*