A Two-Filter Approach for State Estimation Utilizing Quantized Output Data

Filtering and smoothing algorithms are key tools to develop decision-making strategies and parameter identification techniques in different areas of research, such as economics, financial data analysis, communications, and control systems. These algorithms are used to obtain an estimation of the system state based on the sequentially available noisy measurements of the system output. In a real-world system, the noisy measurements can suffer a significant loss of information due to (among others): (i) a reduced resolution of cost-effective sensors typically used in practice or (ii) a digitalization process for storing or transmitting the measurements through a communication channel using a minimum amount of resources. Thus, obtaining suitable state estimates in this context is essential. In this paper, Gaussian sum filtering and smoothing algorithms are developed in order to deal with noisy measurements that are also subject to quantization. In this approach, the probability mass function of the quantized output given the state is characterized by an integral equation. This integral was approximated by using a Gauss–Legendre quadrature; hence, a model with a Gaussian mixture structure was obtained. This model was used to develop filtering and smoothing algorithms. The benefits of this proposal, in terms of accuracy of the estimation and computational cost, are illustrated via numerical simulations.

Optimization of Quantitative Financial Data Analysis System Based on Deep Learning

In order to better assist investors in the evaluation and decision-making of financial data, this paper puts forward the need to build a reliable and effective financial data prediction model and, on the basis of financial data analysis, integrates deep learning algorithm to analyze financial data and completes the financial data analysis system based on deep learning. This paper introduces the implementation details of the key modules of the platform in detail. The user interaction module obtains and displays the retrieval results through data parsing, calling the background, and computing engine. The data cleaning module fills, optimizes, and normalizes the data through business experience; the calculation engine module uses the algorithm and extracts the database information to get the similar time series and matching financial model. Finally, the data acquisition module fills the database with historical data at the initialization stage and updates the database every day. The data analysis platform for quantitative trading designed and implemented in this paper has carried out demand analysis, design, implementation, and test. From the perspective of function test and performance test, two functions of similar stock search and financial matching model are selected and tested, and the results are in line with the expected results.

A review of data mining methods in financial markets

<abstract><p>Financial activities are closely related to human social life. Data mining plays an important role in the analysis and prediction of financial markets, especially in the context of the current era of big data. However, it is not simple to use data mining methods in the process of analyzing financial data, due to the differences in the background of researchers in different disciplines. This review summarizes several commonly used data mining methods in financial data analysis. The purpose is to make it easier for researchers in the financial field to use data mining methods and to expand the application scenarios of it used by researchers in the computer field. This review introduces the principles and steps of decision trees, support vector machines, Bayesian, K-nearest neighbors, k-means, Expectation-maximization algorithm, and ensemble learning, and points out their advantages, disadvantages and applicable scenarios. After introducing the algorithms, it summarizes the use of the algorithm in the process of financial data analysis, hoping that readers can get specific examples of using the algorithm. In this review, the difficulties and countermeasures of using data mining methods are summarized, and the development trend of using data mining methods to analyze financial data is predicted.</p></abstract>

Data analytics by management accountants

Purpose This paper aims to understand how the tasks of management accountants (MA) are affected by data analytics (DA). Design/methodology/approach A qualitative methodology was deemed most appropriate given the exploratory nature of the research questions (RQ). In total, 10 open-ended interview questions were used to gather the evidence. The case study design was inductive, yielding rich data from 29 respondents representing 20 different organizations. Findings Answers were provided to three interrelated RQs about the use of DA by MA, namely, what are their responsibilities? How does this work support inference, prediction and assurance? And how can they ensure insights from DA can be turned into decisions that add value? The findings also indicate that MA have not taken charge of the data analytic opportunities and at present, their activities remain largely focused on descriptive and financial data analysis rather than more complex activities using external data, operational data and modeling. Research limitations/implications The limitation of this research is that it is based on a relatively small, geographically restricted sample (20 organizations in south-central Canada) as well by interviews that were only 60 min in duration. Practical implications Provides a base for the existing practice of management accounting with DA. Social implications Explains the social relationship between DA and management accounting. Originality/value Documented and explained the extent of actual DA use by MA.