Project Report from the year 2018 in the subject Computer Science - Technical Computer Science, course: Computer Science, language: English, abstract: Modeling and Forecasting of the financial market have been an attractive topic to scholars and researchers from various academic fields. The financial market is an abstract concept where financial commodities such as stocks, bonds, and precious metals transactions happen between buyers and sellers. In the present scenario of the financial market world, especially in the stock market, forecasting the trend or the price of stocks using machine learning techniques and artificial neural networks are the most attractive issue to be investigated. As Giles explained, financial forecasting is an instance of signal processing problem which is difficult because of high noise, small sample size, non-stationary, and non-linearity. The noisy characteristics mean the incomplete information gap between past stock trading price and volume with a future price. The stock market is sensitive with the political and macroeconomic environment. However, these two kinds of information are too complex and unstable to gather. The above information that cannot be included in features are considered as noise. The sample size of financial data is determined by real-world transaction records. On one hand, a larger sample size refers a longer period of transaction records; on the other hand, large sample size increases the uncertainty of financial environment during the 2 sample period. In this project, we use stock data instead of daily data in order to reduce the probability of uncertain noise, and relatively increase the sample size within a certain period of time. By non-stationarity, one means that the distribution of stock data is various during time changing. Non-linearity implies that feature correlation of different individual stocks is various. Efficient Market Hypothesis was developed by Burton G. Malkiel in 1991.

The financial market is a very complex nonlinear series of time. There have been a lot of opinions in the topic of the predictability of it. The need to predict a next day, week, or month has always existed for the final purpose of making money. The most common way of forecasting this time series is with statistic methods and linear regression models. However, the use of artificial intelligence algorithms may have a better outcome, due to the capability of them to handle nonlinear data. The present thesis will be focused on evaluating the use of artificial intelligence algorithms as forecasters for financial markets stock prices. Two algorithms will be used, Feed-Forward Neural networks and Adaptive Neuro-Fuzzy Inference Systems (ANFIS). All forecasts are made with the purpose of a short term trading strategy. Three stocks will be used as an example of the consistency of the method; Google, Apple and the Mexican stock ALFA. These three stocks have different distributed data and different behavior from the neural networks and ANFIS ¡s expected.

With exponentially increasing amounts of data accumulating in real-time, there is no reason why one should not turn data into a competitive advantage. While machine learning, driven by advancements in artificial intelligence, has made great strides, it has not been able to surpass a number of challenges that still prevail in the way of better success. Such limitations as the lack of better methods, deeper understanding of problems, and advanced tools are hindering progress. Challenges and Applications of Data Analytics in Social Perspectives provides innovative insights into the prevailing challenges in data analytics and its application on social media and focuses on various machine learning and deep learning techniques in improving practice and research. The content within this publication examines topics that include collaborative filtering, data visualization, and edge computing. It provides research ideal for data scientists, data analysts, IT specialists, website designers, e-commerce professionals, government officials, software engineers, social media analysts, industry professionals, academicians, researchers, and students.

Offers an alternative technique in forecasting to the traditional techniques used in trading and dealing. The book explains the shortcomings of traditional techniques and shows how neural networks overcome many of the disadvantages of these traditional systems.

Exotic methods refer to specific functions within general soft computing methods such as genetic algorithms, neural networks and rough sets theory. They are applied to ordinary shares for a variety of financial purposes, such as portfolio selection and optimization, classification of market states, forecasting of market states and data mining. This is in contrast to the wide spectrum of work done on exotic financial instruments, wherein advanced mathematics is used to construct financial instruments for hedging risks and for investment.In this book, particular aspects of the general method are used to create interesting applications. For instance, genetic niching produces a family of portfolios for the trader to choose from. Support vector machines, a special form of neural networks, forecast the financial markets; such a forecast is on market states, of which there are three OCo uptrending, mean reverting and downtrending. A self-organizing map displays in a vivid manner the states of the market. Rough sets with a new discretization method extract information from stock prices."

Prediction of financial markets, especially prediction of highly volatile stochastic stock market indices, plays a crucial role in identifying profitable investment avenues by the financial investors at large. The investing community encompasses retail investors, financial institutions, investment banks and Foreign Institutional Investors who look for the creation of wealth in the form of capital appreciation and earning the title of ownership of business enterprises by investing in the securities market, through buying and selling of shares of stock exchange listed corporate entities. The forecasting of dynamic financial market movements is one of the scientific endeavours which demands a great deal of market intelligence, financial acumen and domain knowledge of the characteristics of behavioural finance in a wider spectrum. This paper aims to discuss the non-linear movement pattern/trend of the most active two stock indices of India, namely, the Sensex and Nifty, during the study period from 2009-2015 by applying the traditional logistic regression method and one of the neural network tools, namely, k-nearest neighbourhood algorithm. This study would help the investors to streamline their investment patterns and strategies in order to take well informed investment decisions and optimize their stock returns by using the relevant market information.