Financial time series forecasting with deep learning : A systematic literature review: 2005–2019

Dr. Ashenhurst set the tone of the session by saying that the panel would discuss systems analysis in the industrial management sense, "With a view toward coordinating educational programs with management needs".

Systems analysis and design

Stock price modeling and prediction have been challenging objectives for researchers and speculators because of noisy and non-stationary characteristics of samples. With the growth in deep learning, the task of feature learning can be performed more effectively by purposely designed network. In this paper, we propose a novel end-to-end model named multi-filters neural network (MFNN) specifically for feature extraction on financial time series samples and price movement prediction task. Both convolutional and recurrent neurons are integrated to build the multi-filters structure, so that the information from different feature spaces and market views can be obtained. We apply our MFNN for extreme market prediction and signal-based trading simulation tasks on Chinese stock market index CSI 300. Experimental results show that our network outperforms traditional machine learning models, statistical models, and single-structure(convolutional, recurrent, and LSTM) networks in terms of the accuracy, profitability, and stability.

Deep learning-based feature engineering for stock price movement prediction

Stock market prediction has been a classical yet challenging problem, with the attention from both economists and computer scientists. With the purpose of building an effective prediction model, both linear and machine learning tools have been explored for the past couple of decades. Lately, deep learning models have been introduced as new frontiers for this topic and the rapid development is too fast to catch up. Hence, our motivation for this survey is to give a latest review of recent works on deep learning models for stock market prediction. We not only category the different data sources, various neural network structures, and common used evaluation metrics, but also the implementation and reproducibility. Our goal is to help the interested researchers to synchronize with the latest progress and also help them to easily reproduce the previous studies as baselines. Based on the summary, we also highlight some future research directions in this topic.

Applications of deep learning in stock market prediction: recent progress

Deep learning of subsurface flow via theory-guided neural network

Stock market is considered chaotic, complex, volatile and dynamic. Undoubtedly, its prediction is one of the most challenging tasks in time series forecasting. Moreover existing Artificial Neural Network (ANN) approaches fail to provide encouraging results. Meanwhile advances in machine learning have presented favourable results for speech recognition, image classification and language processing. Methods applied in digital signal processing can be applied to stock data as both are time series. Similarly, learning outcome of this paper can be applied to speech time series data. Deep learning for stock prediction has been introduced in this paper and its performance is evaluated on Google stock price multimedia data (chart) from NASDAQ. The objective of this paper is to demonstrate that deep learning can improve stock market forecasting accuracy. For this, (2D)2PCA + Deep Neural Network (DNN) method is compared with state of the art method 2-Directional 2-Dimensional Principal Component Analysis (2D)2PCA + Radial Basis Function Neural Network (RBFNN). It is found that the proposed method is performing better than the existing method RBFNN with an improved accuracy of 4.8% for Hit Rate with a window size of 20. Also the results of the proposed model are compared with the Recurrent Neural Network (RNN) and it is found that the accuracy for Hit Rate is improved by 15.6%. The correlation coefficient between the actual and predicted return for DNN is 17.1% more than RBFNN and it is 43.4% better than RNN.

Stock prediction using deep learning

Computerisation of operations using Management Information System (MIS) has already managed to change the face of Microfinance Institutions (MFIs) in India. The constant growth of Indian microfinance industry prompts the researchers to suggest new IT applications which will play an important role in its success. The paper identifies situations which will require the help of IT to overcome human limitations in decision making. In the process it attempts to empower the managers of the companies by using Decision Support System (DSS) on fund management. The way blood management is to the human body, similarly fund management is to the microfinance organisation. The paper uses literature review and analytical tool like the data flow diagram to help the reader grasp the situation.

Data flow diagram for developing DSS on fund management of Indian microfinance institutions

Purpose – The purpose of this paper is to present a policy comparison tool for Indian Microfinance Institutions (MFIs) so that they can choose the best policy for implementation. It provides for turnaround of a troubled MFI by analyzing the performance of different policies. Design/methodology/approach – The paper has done a web survey to identify the need of a strategic tool for MFI. It has built a Decision Support System (DSS) using system dynamics. A corporate model of MFI has been constructed using iThink 10.0.2 software. A quantitative validity test has been done to find the robustness of the model. Finally four policies are tested and the performance indicators have been used to suggest the best policy. Apart from this DSS is used to test the implementation range of a policy. Findings – “Integration of Microfinance with country’s mainstream financial system along with provisioning 1 percent of outstanding loans” is recommended for the MFI as this will increase the financial performance. Research lim...

System dynamics to turnaround an Indian microfinance institution

This paper gives the reader a tool to handle the current crisis faced by the microfinance industry in Andhra Pradesh, India. Microfinance has gained importance in the Indian and the global economy. This paper highlights the reason for this importance and its success while tracking the evolution of the industry. The paper highlights the global trend of the industry using region-specific parameters. It further analyzes the gradual growth of the Indian microfinance industry in a chronological manner. Finally, the paper highlights the role of technology, especially Decision Support System (DSS), in reducing the volatility of the decisions made by the Microfinance Institutions (MFIs).IntroductionAll the institutions which share a commitment to serving clients with low-incomes that have been excluded from the formal banking sector are part of the microfinance industry (Morduch, 1999). The Consultative Group to Assist the Poorest (the apex association of international donors who support microfinance) regards microfinance as "a powerful tool to fight poverty" that can help poor people to "raise income, build their assets, and cushion themselves against external shocks" (Copestake, 2007).Microfinance-financial services tailored to the poor (Despallier et al., 2011)- spans a range of financial instruments including credit, savings, insurance, mortgages and retirement plans, all of which denominated in small amounts (Khavul, 2010). Historically, efforts to deliver formal credit and financial services to the rural poor in developing countries have failed. The recent proliferation of innovative microfinance programs has been inspired largely by the belief that such programs reach the poor and have a positive impact (Coleman, 2006; and Mallick, 2012).MFIs have reached well over 100 million clients and achieved impressive repayment rates on loans (Cull et al., 2011). Because of the increase in the scale of operations, the concept and practice of microfinance have changed dramatically over the last decade and microfinance is increasingly adopting a financial systems approach, either by operating on commercial lines or by systematically reducing reliance on interest rate subsidies and/or aid agency financial support (Imai et al., 2010). A few MFIs have implemented best business practices and made transition to fully regulated financial institutions. Many more are in the process of undertaking this transformation or at least considering it (Tucker, 2001). Some advocates of innovation say transformation from non-profit to commercial enterprises is the only way to go. It is further believed that this commercialization approach will increase MFIs' operational efficiency, sustainability and the outreach, and decrease the dependency on the donor agencies (Floque et al., 2011).A Brief Overview of Microfinance IndustryImportance of Microfinance IndustryThe importance of microfinance industry in achieving the Millennium Development Goals as well as national policies that target poverty reduction, empowering women and improving standard of living, is that it acts as a flexible development tool, permanent and widespread (Asiama, 2007; and SAVESCU, 2010).In the study entitled "Is Microfinance an Effective Strategy to Reach the Millenium Development Goals?", Elizabeth Littlefield, Jonathan Murduch and Syed Hashemi, state :Studies of global or regional level among the millions of customers of microfinance institutions show that the access to funding sources has allowed the poor to increase household and family income, to purchase goods and to reduce the impact that certain unforeseen events may have on them. (SAVESCU, 2010)However, some of the authors have argued that microcredit is not a panacea for poverty-alleviation and that in some cases the poorest people have been made worse-off (Asiama, 2007).This notwithstanding, the UN declared 2005 to be the International Year of Microcredit (Hermes and Lensink, 2007). …

The Growth of Microfinance and the Role of DSS in Reducing Its Volatility

This paper gives the reader a tool to handle the current crisis faced by the microfinance industry in Andhra Pradesh, India. Microfinance has gained importance in the Indian and the global economy. This paper highlights the reason for this importance and its success while tracking the evolution of the industry. The paper highlights the global trend of the industry using region specific parameters. It further analyzes the gradual growth of the Indian microfinance industry in a chronological manner. Finally, the paper highlights the role of technology, especially Decision Support System (DSS), in reducing the volatility of the decisions made by the Microfinance Institutions (MFIs).

Ritika Singh

Papers

Stock prediction using deep learning

Data flow diagram for developing DSS on fund management of Indian microfinance institutions

System dynamics to turnaround an Indian microfinance institution

The Growth of Microfinance and the Role of DSS in Reducing Its Volatility

The Growth of Microfinance and the Role of DSS in Reducing its Volatility