Data Analysis

In customs management, the main problem is balancing the needs of trade facilita-tion as a process of simplifying and accelerating foreign business on the one hand and countering illegal trade, reducing government revenue, capital sleep and the level of controls and interventions on the other. Also, due to the financial crisis in recent years, risk management has been reconsidered, although this attention is related to various financial branches. Since risk analysis and identification is the main component of risk management, developing a suitable model for data analysis is of particular importance. The purpose of this study was to use data data analysis techniques to develop an intelligent model to timely predict the risk of import declarations in customs and thus prevent irreparable losses. In this study, data analysis techniques have been used according to the statistical population which is data-driven. Statistical data were extracted from www.eplonline.ir with 575006 import declarations of all Iranian customs during 2019-2020. having pre-processed and prepared the data using PCA, LDA and FastICA methods, attribute reduction and effective attribute extraction were performed using 14 data analysis algorithms. Using Python software, algorithms were trained and modeled with 80% of the final data. Then, 14 obtained models were tested and validated with 20% of the data. Finally, the results of these models were compared with each other and the model obtained from the random forest algorithm was selected as a comprehensive model for predicting and determining the level of risk of import declarations at customs.

In healthcare, a diagnosis is reached after a thorough physical assessment and analysis of the patient's medicinal history, as well as the utilization of appropriate diagnostic tests and procedures. 1.7 million People worldwide lose their lives every year due to complications from chronic kidney disease (CKD). Despite the availability of other diagnostic approaches, this investigation relies on machine learning because of its superior accuracy. Patients with chronic kidney disease (CKD) who experience health complications like high blood pressure, anemia, mineral-bone disorder, poor nutrition, acid abnormalities, and neurological-complications may benefit from timely and exact recognition of the disease's levels so that they can begin treatment with the most effective medications as soon as possible. Several works have been investigated on the early recognition of CKD utilizing machine-learning (ML) strategies. The accuracy of stage anticipations was not their primary concern. Both binary and multiclass classification methods have been used for stage anticipation in this investigation. Random-Forest (RF), Support-Vector-Machine (SVM), and Decision-Tree (DT) are the prediction models employed. Feature-selection has been carried out through scrutiny of variation and recursive feature elimination utilizing cross-validation (CV). 10-flod CV was utilized to assess the models. Experiments showed that RF utilizing recursive feature removal with CV outperformed SVM and DT.

Today, users generate various data increasingly using the Internet when choosing a product or service. This leads to the generation of data about the purchases and services of various consumers. In addition, consumers often leave feedback about the purchase. At the same time, consumers discuss their attitudes about goods and services on social networks, messengers, thematic sites, etc. This leads to the emergence of large volumes of data that contain useful information about various manufacturers of goods and services. Such information can be useful to both ordinary users and large companies. However, it is practically impossible to use this information due to the fact that it is located in different places, that is, it has a raw, unstructured character. At the same time, depending on the target group of users, not the entire data set is needed, but a specific target sample. To solve this problem, it is necessary to have a tool for structuring information arrays and their further analysis depending on the set goal. This can be done with the help of various frameworks that use methods of machine learning and work with data. This work is devoted to elucidating the problem of creating means for evaluating consumer preferences based on the analysis of large volumes of data for its further use by the target audience.  The goal of the development of big data analysis systems is obtaining new, previously unknown information. The methodology of application of algorithms of work with large data sets and methods of machine learning is used, namely the pandas library for operations on a data set and logistic regression for information classification As a result, a system was built that allows the analysis of lexical information, translate it into numerical format and create on this basis the necessary statistical samples. The originality of the work lies in the use of specialized libraries of data processing and machine learning to create data analysis systems. The practical value of the work lies in the possibility of creating data analysis systems built using specialized machine learning libraries.