Sharif Digital Repository

In this study we are looking for an optimum way to select a multi-asset portfolio. Usually portfolios only contain stocks and bonds. Here we examine if adding other sort of assets like gold, currencies, bank deposit and gilt-edged securities are optimum or not. We are doing a comprehensive research of adding other kinds of assets to the portfolio. With modeling and solving the real situation, data and constraints of Iranian financial market we decide to whether add other assets to our portfolio or not. The results show in recent years low risk assets are optimum to add to the portfolio as it is was anticipated to the major economic of Iran  

In this work, effects of information aggregation on risk attitude of Iranian individuals is being studied through two experiments. In these experiments a risk-free asset with a guaranteed revenue and a risky asset is introduced to each individual. Then the individual has to allocate a certain amount of money between two assets. In both experiments three treatments of control, separation and aggregation are defined in a way that the degree of information aggregation increases respectively. Given the specific treatment assigned to each individual, complementary information is presented, in orderto finalize the decision. Next a financial market simulation for a five year horizon is conducted to... 

Textual news published in the media on a daily basis is a large and valuable source of unstructured data that can be used to analyze and model the financial market by using text mining methods. The purpose of this study is to design a news-reading system for economic analysis and modeling of gold prices using features extracted from textual news and text mining methods; it seeks to enable the machine to read news like financial analysts then analyze and forecast the economic situation and market trends. For this purpose, we collected news from the website of an Iranian economic news agency. To design the economic analyzer, we extracted important economic, political, and social factors from... 

Generally, nowadays, machine learning methods are used in many different areas for their superiority over other methods of prediction. Although being a tough task, stock market prediction with machine learning approaches is being spread due to satisfying results published ever yday. Machine learning methods usually use varied kinds of data ,including structured data such as market data, technical indicators and some fundamental data as well as unstructured one entailing text and graph data in order to enhance their predictability capacity. In this thesis we aimed to find out more about the importance and the contribution of structured data in prediction and we tried to attain a framework... 

Forecasting and analysing financial markets has always been an interesting research topic for fields ranging from financial sciences to mathematics and statistics. With the rapid development of artificial intelligence in the recent years, there has been a growing interest in using deep neural networks to predict market future trends. The price in these markets is determined by mechanisms of demand and supply. When there is a tendancy to buy a stock, there will be an increase in demand resulting a positive growth for price. On the other hand, when a large group of investors decide to sell their assets, market will experience an increase in supply and subsequently the prices drop. Availability... 

Throughout history, forming an optimal asset portfolio has been the primary goal of capital owners and managers of investment funds in any economic activity. Achieving this goal is equivalent to trying to minimize the risk caused by the inevitable fluctuations in the capital market and maximizing the overall investment return during the expected period. Investors can operate in various financial markets where there are different stocks and asset classes in each of these markets. The main goal of investors is to identify profitable stocks and form an optimal asset portfolio based on them.Based on this, during the past decades, many studies have been conducted to form and optimize the stock... 

The use of machine learning and deep learning tools to predict the future behavior of trends in massive data requires the extraction and creation of the eigenvector for the chosen model in the problem. It should be noted that simply by increasing the number of features, it cannot be expected that the learning model will have a higher efficiency. Rather, the quality and importance of the features in the field under study should be carefully considered. Topics such as data redundancy, data correlation, the amount of information in the data, distorted data, outliers, etc. are important steps in improving the dataset and creating a feature vector for training the learning model. In the realm of... 

With the rapid development of the economy, more people have started investing in the stock market. Predicting price changes can reduce the risk of investing in stocks. Technical data such as price and volume in the stock market is usually used to predict stock prices, and less often other types of data such as market data or fundamental data are used. In this study, we want to determine what impact each of the available data types has on stock prices. For example, data of buy and sell for per capita, capital inflows and outflows for small and large natural and legal investors, information related to the stocks themselves, indicators, fundamental data such as earnings per share (EPS) and... 

The problem of stock price direction prediction is of great value among investors and researchers in the past decades. Even the smallest improvement in the performance of forecasting methods can lead to noticeable profit for investors. In this regard, in this research, a new method for filling the literature gap in the field of stock price direction forecasting is proposed. In the proposed method, two concepts of dynamics and model selection in dealing with data is investigated. Finally a predictive model is developed according to the two abovementioned concepts. Moreover, in this work, using a meta-learning approach one step towards making the prediction process automatic is taken. The... 

For along time, analysis of financial markets is an interesting topic for mankind. There are different statistical methods to analyze financial time series. In this manuscript, financial markets are analyzed from network view point. Inference of hidden structures between companies of a market is merit information so we introduce different methods to infer
hidden network structure of financial markets. In addition, we will show that dynamic of network structure can provide important information about external sources of influence on financial markets. Actually, we show affect of political events on financial market of Iran. At last, we generalize diffusion concept at financial networks... 

Estimation of indirect economic losses due to natural disasters, especially earthquakes, is one of the essential issues in disaster management. This study presents a framework that uses an economic model of the community under study and calculates the indirect economic losses caused by an earthquake. To this end, first, the earthquake-induced direct economic losses are quantified using appropriate risk analysis models. The direct losses are used to characterize the consequent shock to labor and capital. These shocks are then used as inputs to the regional economic model. In the proposed framework, a Computable General Equilibrium (CGE) model uses various data about the state of the community... 

Price to earnings ratio is one of the most used ratios in financial markets for valuation of firms in the Iran and world. In present research for analysis of this ratio,investors’ sentiment alongside fundamental factors affecting price to earnings ratio has been investigated. Fundamental factors affecting this ratio are selected based on prior research and economics theory; these factors are, dividend ratio, growth,risk and inflation. For the analysis of investors’ sentiment, eight proxies related to sentimental behavior have been utilized; among them, four are introduced and used for the first time in this research. Implementing these eight sentimental proxies, a variable measuring... 

Algorithmic trading in financial markets with machine learning is a developing and promising field of research. Financial markets have a complex, uncertain, and dynamic nature, making them challenging for algorithmic trading. To cope with the challenges of algorithmic trading in financial markets, we propose a multi-agent deep reinforcement learning framework trained by Deep Q-learning (DQN) algorithm to perform financial trading. This framework consists of multiple cooperative agents, each of which trained on a specific timeframe, to perform financial trading on the collective intelligence of the agents. Numerical experiments are conducted on historical data of the EUR/USD currency pair.... 

Price movement prediction has always been one of the traders’ concerns in the field of financial market prediction. In order to increase the profit of the trades, the traders can process the historical data and predict the movement. The large size of the data and complex relations between them lead us to use algorithmic trading and artificial intelligence.The stock and Cryptocurrency markets are two common markets attracting traders. This thesis aims to offer an approach using Twin-Delayed DDPG (TD3) and daily close price in order to achieve a trading strategy. Unlike the previous studies using a discrete action space reinforcement learning algorithm, TD3 is a continuous one offering both... 

Many different scaling laws are observed in financial data. As an example, the distribution of Log-Return of stock prices obey power law, provided relatively short time intervals are considered. In standard statistical physics, scaling laws are observed in critical phenomena, where the system has long-ranged correlations. Within the same context, to arrive at criticality one has to tune some external parameters, such as the temperature. Yet, there are a group of systems that tend towards criticality through their dynamics. Such systems are called self-organised critical systems.There have been proposed many different mechanisms and models to address why power laws are observed in financial... 

Over the past few years, deep reinforcement learning(DRL) has been given a lot of attention in finance for portfolio management. With the help of experts’ signals and historical price data, we have developed a new reinforcement learning(RL) method. The use of experts’ signals in tandem with DRL has been used before in finance, but we believe this is the first time this method has been used to solve the financial portfolio management problem. As our agent, we used the Proximal Policy Optimization(PPO) algorithm to process the reward and take actions in the environment. Our framework comprises a convolutional network to aggregate signals, a convolutional network for historical price data, and...