scholarly journals Development of International Agricultural Trade Using Data Mining Algorithms-Based Trade Equality

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Liu Yan
Keyword(s):  
Data Mining ◽  
Data Analysis ◽  
Agricultural Trade ◽  
Machine Learning Techniques ◽  
Trade Data ◽  
Data Mining Algorithms ◽  
Efficient Data ◽  
Using Data ◽  
Analysis System ◽  
Data Analysis System

The development of international agriculture trade during the COVID-19 pandemic has encountered significant challenges. The processing of international agricultural trade data using machine learning techniques needs to be improved to perform effective analysis of agricultural trade. An essential issue for international agricultural trade is the accurate yield estimation for the numerous crops involved in international trade. Data mining techniques are the necessary approach for accomplishing practical and effective solutions for this problem. This paper combined the bidirectional encoder representations from transformers (BERT) model to conduct data mining and developed a trade data analysis system with efficient data analysis capabilities. Our results indicate that our model does reasonably well and obtains adequate information in deciding international agricultural trade. It can also be instrumental for policy and decision-making regarding international agricultural trade.

scholarly journals Prediction of Mortality Rate of COVID-19 Patients using Machine Learning Techniques in Nigeria

2020 ◽  
Vol 9 (5) ◽  
pp. 30-34
Author(s):  
Agbelusi Olutola ◽  
Olayemi Olufunke C
Keyword(s):  
Data Mining ◽  
Mortality Rate ◽  
Online Survey ◽  
Virus Disease ◽  
Machine Learning Techniques ◽  
Multilayer Perception ◽  
Data Mining Algorithms ◽  
Corona Virus ◽  
Prediction Of Mortality ◽  
Using Data

Corona virus disease pandemic have highly destructive effects around the world and this virus has affected both developed and developing nations. In this paper, predictive model for the mortality rate of patients infected with corona virus in Nigeria using data mining techniques is developed. Oral interview was conducted with virologist at health institution (The Federal medical centre, Owo, Ondo state, Nigeria) to ask for some basic factors that causes mortality in infected corona virus patients. Online survey was done based on these ten basic factors and three hundred and two responses were collected and preprocessed. A ten fold cross validation technique was used to partition the datasets into training and testing data in which predictive models were developed using data mining algorithms (Multilayer Perception, Naïve Bayes, Decision Tree and Decision Rule) . Waikato Environment for Knowledge Analysis (WEKA) was used to simulate the models and the result shows that the four models developed have the capability to forecast mortality rate of corona virus adequately. Conclusively, multilayer perception has the highest level of performance with 85% accuracy. Multilayer Perception model is effective, reliable and is recommended to forecast the rate of mortality of patients infected with corona virus. Moreover, this prediction is important because the death of any patients is emotional and physically challenging to the morning families

scholarly journals Data Mining technologies in managing the assortment of trading companies

2021 ◽  
Vol 16 (91) ◽  
pp. 99-109
Author(s):  
Lyudmila N. Loginova ◽  
◽  
Alexander M. Shash ◽  
Keyword(s):  
Data Mining ◽  
Customer Service ◽  
Sustainable Competitive Advantage ◽  
Joint Work ◽  
Data Mining Algorithms ◽  
Using Data ◽  
Analysis System ◽  
The Stability ◽  
Fierce Competition ◽  
Mining Algorithms

In the conditions of fierce competition, satisfaction of all customer needs provides a trading enterprise with a sustainable competitive advantage. With the traditional structure of the assortment, there is a decrease in both the potential and real level of profit, the loss of competitive positions in promising markets, and, therefore, there is a decrease in the stability of the enterprise. The development of an analysis system to determine the specifics of the product range, optimize the range, and adapt it to the conditions of the Russian market is undoubtedly an urgent task. This article provides an overview of trade and IT companies that use data mining technologies. The survey showed that many companies are using data mining technology to improve customer service, turnover and sales in stores. In this regard, the management of Familia decided to develop its own software that will combine the analysis of turnover and sales in the company's stores in order to increase sales and improve the placement of goods in stores so that the client buys the necessary things, increasing the company's profit. The paper shows the possibility of combining several data mining methods in one system; shows the results of the analysis system and shows the effectiveness of the developed analysis system at Familia. The uniqueness of the developed software is the combination of data mining algorithms into one software product. The developed analysis system, based on the joint work of two data mining algorithms K-means and Apriori, allows you to manage the range of trade enterprises, reducing company losses.

scholarly journals Discussion on the Application of Enterprise Business Intelligence Data Analysis System

2021 ◽  
Vol 5 (4) ◽  
pp. 23-26
Author(s):  
Ning Yang
Keyword(s):  
Data Mining ◽  
Data Analysis ◽  
Business Intelligence ◽  
Customer Requirements ◽  
Analysis System ◽  
Data Analysis System ◽  
Comprehensive Processing

Enterprise Business Intelligence (BI) system refers to data mining through the existing database of the enterprise, and data analysis according to customer requirements through comprehensive processing. The data analysis efficiency is high and the operation is convenient. This paper mainly analyzes the application of enterprise BI data analysis system in enterprises.

scholarly journals Big data sets in construction

2019 ◽  
Vol 110 ◽  
pp. 02007
Author(s):  
Pavel Kagan
Keyword(s):  
Data Mining ◽  
Big Data ◽  
Data Analysis ◽  
Text Analysis ◽  
Text Messages ◽  
Data Conversion ◽  
Data Sets ◽  
Analysis System ◽  
The Moment ◽  
Data Analysis System

The paper studies the processing of large information data arrays (Big Data) in construction. The issues of the applicability of the big data concept (Big Data) at various stages of the life cycle of buildings and structures are considered. Methods for data conversion for their further processing are proposed. The methods used in the analysis of "big data" allow working with unstructured data sets (Data Mining). An approach is considered, in which the analysis of arbitrary data can be reduced to text analysis, similar to the analysis of ordinary text messages. At the moment, it is important and interesting to isolate non-obvious links present in the analysed data. The advantage of using big data is that it is not necessary to advance hypotheses for testing. Hypotheses appear during data analysis. Dependence analysis is a basic approach when working with big data. The concept of an automatic big data analysis system is proposed. For data mining, text analysis algorithms should be used, and discriminant functions should be used for the main problem to be solved (data classification).

scholarly journals Student Learning Prediction Using Machine Learning Techniques

2019 ◽  
Vol 8 (6) ◽  
pp. 4179-4183
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Student Performance ◽  
Machine Learning Techniques ◽  
Data Mining Algorithms ◽  
Learning Techniques ◽  
Final Exams ◽  
E Learning ◽  
Using Data ◽  
Mining Algorithms

Now a day’s e-learning is smartly growing technology. This technology is more helpful for students to communicate with their professors through chats or emails. ELearning also removes the obstacle of physical presence of an Elearner. The main aim of this paper is to predict student performance in their final exams using different machine learning techniques. Information like attendance, marks, assignments, class participation, seminar, CA, projects and semester are collected to predict student performance. This prediction helps the instructors to analyze their students based on their performance. For that we have used WEKA tool for the prediction of the student performance. WEKA (Waikato Environment for Knowledge Analysis) is one of the data mining too which is used for the classification and clustering using data mining algorithms. This prediction helps the students and the staffs to know how much effort their students need to be put in their final exams to get good marks.

Sign in / Sign up

Export Citation Format

Share Document