This document discusses using neural networks for financial forecasting. It explains that neural networks can be trained on nonlinear and non-stationary financial data to predict things like stock and commodity prices without restricting models. The document outlines different neural network architectures like NARX models and techniques like backpropagation for training. It also discusses challenges like limited data, noise and non-stationarity. The document demonstrates applying different preprocessing techniques like moving average, FFT and HHT to interest rate, stock and exchange rate data in neural networks, finding that preprocessing can improve performance.
Breaking the Kubernetes Kill Chain: Host Path Mount
Financial forecastings using neural networks ppt
1. FINANCIAL FORECASTING USING NEURAL NETWORKS Presented by , Amit jain 07000519Ranjeet ranjan 07000537puneet gupta 07000534
2. What is Financial Forecasting Prediction of prices of instruments of speculation Stocks Commodity futures Exchange Rates Interest Rates . Problem : Non linear and non stationary data
3. Methods Used Fundamental Analysis Understanding the supply demand curve Involves studying of news and economic factors Technical Analysis Understanding historical price patterns Tools like moving average, learning systems Latest Approach: Combine Technical and Fundamental Analysis
4. NEURAL NETWORKS Map some type of input stream of information to an output stream of data. They derive non-linear modelsthat can be trained to map past and future values of the input output relationship .It extracts relationships governing the data that was not obvious using other analytical tools. Capability to recognize patternand the speed of techniques to accurately solve complex processes, exploited exhaustively in financial forecasting. Trained without the restriction of a model to derive parameters and discover relationships, driven and shaped solely by the nature of the data.
5. NEURAL NETWORKS V/S CONVENTIONAL COMPUTERS Neural networks have the unique capability of learning thus are adaptive .This problem solving tool creates a unique likeness to the human brain . Use the interconnectedness of the elements of the model rather than follow a set of sequential steps, that may or may not solve the problem like computers do. A different aspect of model building, where the unique relationships between the variables creates the model, rather than trying to force variables to conform to a theoretical abstract that may or may not exist.
6. NEURAL NETWORKS IN FINANCE Neural networks are trained without the restriction of a model to derive parameters and discover relationships, driven and shaped solely by the nature of the data. Thus it has profound implications and applicability to the finance field. Some of the fields where it is applied are: Financial forecasting Capital budgeting and risk management Stock market analysis Used to analyze and verify Economic hypothesis and theories which were not possible otherwise. Govt. predicts interest rates to gauge the future inflationary situation of its economy .
18. TIME SERIES FORECASTING Time series forecastingor time series prediction, takes an existing series of data and forecasts the data values. The goal is to observe or model the existing data series to enable future unknown data values to be forecasted accurately. Done using the NARX model or NAR model .
19. DIFFICULTIES Limited quantity of data . Noise in data – It obscures the underlying pattern of the data . Non-stationarity - data that do not have the same statistical properties (e.g., mean and variance) at each point in time Appropriate Forecasting Technique Selection .
20. Preprocessing of Training Data Reason: Need to understand underlying patterns. Tools: Moving Average Fast Fourier Transform (FFT) Hilbert Huang Transform (HHT)
21. Types Of Data Worked Upon Interest Rates (RBI 91 day Govt. Of India Treasury Bills) Sensex Data ( 2005-2010) Exchange Rates (Daily Exchange Rates of INR-Dollars 2004-2011) All the Data are divided into Three Sets Training Set Testing Set Validation Set
22. Types Of Preprocessing No Pre-Processing (Simple NN) Using FFT (FFT NN) Using HHT (HHT NN) All the types of data are used on all the types of preprocessing techniques , therefore generating 9 cases. Now, we Compare all of them Data-Wise.
23. 1. Interest Rates The interest rate data is applied on all three kinds of preprocessing. The Error Graphs are as: Simple NN
32. Conclusion from Results Pre-processing can boost the Neural Network Performance The performance of Neural Network also depends on the nature of the data series