1. Introduction
ZFS is a monetary organization that gives credits to people and organizations. As an organization working in a profoundly serious and dynamic business climate, ZFS should use innovation to remain in front of the opposition. One of the critical difficulties that the organization faces is the need to deal with a lot of credit information precisely and productively.
The proposed programming arrangement intends to address this test via robotizing the credit information handling work process utilizing Python. The arrangement will empower ZFS to stack the credit information into memory from the two information records given by the DBA (FG Assis et al. 2019).These datasets contain data about past advance records, including the advance candidate’s orientation, conjugal status, wards, instruction, work status, financial record, and property region.
Furthermore, the level of graduate candidates that had their credit status endorsed will be figured. Carrying out this arrangement will essentially affect ZFS. In the first place, the organization will actually want to handle credit information quicker and all the more effectively, decreasing the time and assets expected for this assignment. Second, the exactness and consistency of advanced information handling will be improved, decreasing the gamble of mistakes and guaranteeing consistency with guidelines.
Third, the arrangement will empower ZFS to examine credit information all the more successfully, giving experiences that can illuminate business choices and further develop client support
The purpose of using the programming software named Python is to solve the issues in the loan data which is prepared by the several banks to provide and to store the confidential information of the customers safe and useful for the future according to this project.
There is a large scope of using the different tools and techniques as the demand of using the technological tool by the business are much in demand as it can provide the business with lots of aid in the business calculations , loading the proper structure of the database as well as to protect the data from any cyber crimes or attacks in the future by which the decline of business can be happened. So a sophisticated online compiler of Python named Google Colab is used in the loan data analysis.
The big companies like the ZFS can use the software for their improvement of the business environment because it can hold a huge number of databases for the organization and different types of data analysis can be done for the respective company to maintain its sustainability and productivity in the business. As it is an agricultural and transport industry, multiple forms of data variables can be integrated in the data on which several descriptive analyses can be done.
2. Approach
Requirements
There are a large number of procedures and techniques by which the business data analysis can be done. In this report , the process that is initiated to solve the business issues of loan is implementation of programming language (Chang et al. 2019).. Programming language is used to run several pseudocodes and flowcharts that are executed in the compiler as codes and generated diagrams which can be helpful to illustrate the different aspects of the data in the datasets that have been provided by the respective organization. In task 1 of this project , programming software named Python is used for performing the data analysis on the two separate datasets that are given in the xlsx and pdf format respectively (Sahoo et al. 2019). The two datasets initially converted into csv formats by the user as the Python tool require the datasets in the csv format to perform and execute the codes based on that csv data. Google Collab named online software is used for executing the codes of python because it is easy to operate and understand the use of different libraries. In this Google Colab online server a proper internet connection is required to access the preloaded modules and libraries along with the new imported libraries by the user to execute the codes for the dataset efficiently (Kulothungan et al. 2021).
Figure 1: SDLC
Source: (www.google.com)
SDLC is a term often used in the business data analysis of several projects. It is basically known as the software development life cycle (Li et al. 2022). High quality softwares is built through this phase of the software development process as it is a very time and cost efficient procedure which is mostly used by the development authorities of the software companies to build and modify the high quality based softwares. SDLC passes through the different stages of checking and monitoring phases by which the software is prepared that can be useful in fulfilling the customer demands and expectations and the business authority can be benefited for the future productivity in the business (Anand et al. 2022). Project risks can be handled very easily as the software learns and inherits the software requirements to tackle the customer needs in the organization. SDLC involves the various phases that are defining, designing, coding, testing , deployment of code, maintenance as well as the requirement analysis (ADEBIYI et al. 2022). There is also a concept and utility of the functional and nonfunctional requirements in the business organizations softwares which is very useful in the growth of the business. Functional requirements in the software means the testing of API, testing of the integration of the modules used in the backend, checking of the system (Mambang et al. 2023). Non functional requirements are the things which can be tested to check the usability of the software in terms of the performance , security and much more. In the non-functional requirements of Python , the user can enjoy and understand the coding execution very easily as it is done in this report. Python allows the user to use several libraries that have a specific need of executing the codes. Google Colab server is used for the execution of the codes as it is very suitable for writing and executing the codes of python programming language (Georgeb et al. 2021). The compile time is very quick and the error definition is also very clear so that the programmer can understand the error and rectify in a short period of time (Ciurea et al. 2022). The format of the Google Colab is also very attractive as it can attract and make a level of interest for the coding for the developers and the programmers . Every sort of code in this server can be compiled sequentially and in a different coder section. Each new line of code consists of two parts: texts and code (Chang et al. 2020). The programmer can add the section of the coding part and write the efficient code according to the points, it can help the programmers to understand which part of code is signifying which properties and solutions (Shinde et al. 2019).
Design
In this portion, the important libraries as well as the process that is used for the data cleaning and data visualization is discussed in brief.
In the above figure, the essential libraries are being imported after the dataset is being dragged and dropped from the local directory. The libraries that are imported here are used for the different purposes of the analysis. Pandas library is used here in the Google Colab mainly to load the csv data and convert it into dataframe , so pandas library is very effective in the data manipulation and the datasets conversion (Hemachandran et al. 2021). Another important library that is imported is the numpy library that is used for the basic mathematical statistical calculation so it is also one of the important libraries that should be imported in the beginning. The Seaborn library that is used in the compiler handles advanced mathematical calculation which integrates all the functions to solve and predict the standard form of calculation (Sai et al. 2023). Matplot library is used for the generation and plotting of visual representation of data with diagrams that can be useful for predicting the data in an interesting manner. Warning library is used for the depreciating warnings related to data. After importing the several libraries , the dataset is being imported for the first dataset and the shape of the data in the dataset is also printed respectively using the print function .
In the above figure , a descriptive analysis is done or it can be said exploratory data analysis has been done which depicts the information of datasets by generating a pivot table that frames the data values by rows and columns respectively so that the further analysis can be done respectively. Each column specifies the different values by which a user or coder can understand the data and do the further modifications in the data.
In the above figure, the dataframe column is defined in an index which has several types of data values , some data can be missing and some duplicate data occurrence can also be there. So to avoid those disturbances and problems in data , a code has been written which drops the NA values from the dataframe for the better mathematical calculations. Again a code is being written which drops or delete the duplicate data in the data frame table or pivot table that is being generated.
Testing
There are two types of testing that can be performed by the senior developers and programmers of the software that can check the internal as well as external issues to maintain the usability of the code execution in the software and it is also used to check the other issues related to connection and runtime environment which is very crucial for the testing of codes that are written in the programming softwares. Black box testing refers to the work related to the development of the software and it is not assumed by the tester. The user or tester only deals with the input he is giving on those codes and the results obtained . White box testing is connected with the user or th programmer who writes code , set up the algorithms and the methods used by him to develop or execute the datasets The testing features of the black box is related with the softwares to check the usability to run the softwares and to specify all the functionalities by which a coder or programmer can write programs in the software
Black-Box Testing
Black Box testing refers to the checking and assessment of the internal part of the softwares where the copd and programmer have no ideas as it is the department of the developers and the software designers who design the platform for the execution of the different codes and libraries by which the data analysis can be done. There can be many sections of the testing of the softwares by the developers that integrate the root cause of the run time environment , missing of the packages that are pre installed in the softwares to execute and perform the algorithms by the coders and the programmers.
White-Box Testing
White box testing refers to the part of the coders or the programmers who used to generally write codes and analyze the datasets in the softwares. In this part of the report the white box testing is done by the user who analyzes the datasets and converts the datasets in teh csv format and checks the further part of the algorithm implementations. Several libraries that are used and implemented in order to do the calculations and evaluate the diagrams are categorized in the white box testing. So white box testing is the ultimate goal and step that is done by the coder or the programmer to check if all the codes are executing properly or not. If codes are not running properly, the black box testing is done accordingly by the developers. Hence white box testing is the final process of checking the utility of the software.
3. Recommendation
There is a large scope of using the different tools and techniques as the demand of using the technological tool by the business are much in demand as it can provide the business with lots of aid in the business calculations , loading the proper structure of the database as well as to protect the data from any cyber crimes ort attacks in the future by which the decline of business can be happened. So a sophisticated online compiler of Python named Google Colab is used in the loan data analysis. The big companies like the ZFS can use the software for their improvement of the business environment because it can hold a huge number of databases for the organization and different types of data analysis can be done for the respective company to maintain its sustainability and productivity in the business. Hereby it is recommended that python should be used for more business analysis and according to this report and dataset that has been used some more models should be integrated to perform complex calculations in the dataset like the linear regression model which can predict the future values through machine learning algorithms.
4. Conclusion
The proposed programming arrangement utilizing Python will empower ZFS to robotize credit information handling, further develop effectiveness, and increment precision. By utilizing innovation to handle a lot of credit information, the organization will actually want to remain in front of the opposition and fulfill client needs in an opportune and successful way. The arrangement will likewise empower ZFS to perform exploratory information investigation on credit information, giving bits of knowledge that can illuminate business choices and further develop client care. With the capacity to figure measurements, for example, the level of female candidates that had their credits supported and the normal pay, all things considered, ZFS will actually want to settle on information driven choices and deal fitted advance items to its clients. By and large, the proposed arrangement will altogether affect ZFS, further developing advanced information handling velocity, exactness, and proficiency. The organization will actually want to give better client care and settle on information driven choices to work on its tasks and increment productivity.
Not executing this arrangement would imply that ZFS would keep on depending on manual credit information handling, restricting its capacity to deal with advance information at scale and may bring about lost open doors and diminished consumer loyalty.The arrangement will then complete information groundwork for investigation, including amending copies, missing qualities, and exceptions. Then, the arrangement will perform exploratory information examination on the advance information, which incorporates figuring measurements, for example, the level of female candidates that had their credits endorsed, the normal pay, everything being equal, the normal pay of all candidates that are independently employed, the normal pay of all candidates that are not independently employed, and the typical pay of every alumni candidate.
Reference
Chang, H.C., Wang, C.Y. and Hawamdeh, S., 2019. Emerging trends in data analytics and knowledge management job market: extending KSA framework. Journal of Knowledge Management, 23(4), pp.664-686.
FG Assis, L.F., Ferreira, K.R., Vinhas, L., Maurano, L., Almeida, C., Carvalho, A., Rodrigues, J., Maciel, A. and Camargo, C., 2019. TerraBrasilis: a spatial data analytics infrastructure for large-scale thematic mapping. ISPRS International Journal of Geo-Information, 8(11), p.513.
Sousa, M.J., Pesqueira, A.M., Lemos, C., Sousa, M. and Rocha, Á., 2019. Decision-making based on big data analytics for people management in healthcare organizations. Journal of medical systems, 43, pp.1-10.
Mišić, V.V. and Perakis, G., 2020. Data analytics in operations management: A review. Manufacturing & Service Operations Management, 22(1), pp.158-169.
Sahoo, K., Samal, A.K., Pramanik, J. and Pani, S.K., 2019. Exploratory data analysis using Python. International Journal of Innovative Technology and Exploring Engineering (IJITEE), 8(12), p.2019.
Kulothungan, A., 2021. Loan Forecast by Using Machine Learning. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(7), pp.894-900.
Li, M., 2022. Teaching Data Mining Online to Business Undergraduate Students Using Python. Business Education Innovation Journal, pp.73-81.
Anand, M., Velu, A. and Whig, P., 2022. Prediction of loan behaviour with machine learning models for secure banking. Journal of Computer Science and Engineering (JCSE), 3(1), pp.1-13.
ADEBIYI, M.O., ADEOYE, O.O., OGUNDOKUN, R.O., OKESOLA, J.O. and ADEBIYI, A.A., 2022. SECURED LOAN PREDICTION SYSTEM USING ARTIFICIAL NEURAL NETWORK. Journal of Engineering Science and Technology, 17(2), pp.0854-0873.
Mambang, M., 2023. A Framework for Illegal Online Loan Risk Using WordCloud and Big Data Analytics.
Ka, H., Georgeb, P.M., Rodriguezc, R.V., Kulkarnid, R.M. and Roye, S., 2021. Performance Analysis of KN earest Neighbor Classification Algorithms for Bank Loan Sectors. Smart Intelligent Computing and Communication Technology, 38(9).
Ciurea, C., CHIRIȚĂ, N. and NICA, I., 2022. A PRACTICAL APPROACH TO DEVELOPMENT AND VALIDATION OF CREDIT RISK MODELS BASED ON DATA ANALYSIS. Economic Computation & Economic Cybernetics Studies & Research, 56(3).
Chang, Y.C., Chang, K.H. and Huang, Y.H., 2020. A novel fuzzy credit risk assessment decision support system based on the python web framework. Journal of Industrial and Production Engineering, 37(5), pp.229-244.
Shinde, G., Pawar, S., Albhar, R., Yadav, A. and Patil, M.P., Home-Credit Risk Analysis and Prediction Modelling using Python.
Hemachandran, K., Rodriguez, R.V., Toshniwal, R., Junaid, M. and shaw, L., 2021. Performance analysıs of different classıfıcatıon algorıthms for bank loan sectors. In Intelligent Sustainable Systems: Proceedings of ICISS 2021 (pp. 191-202). Singapore: Springer Singapore.
Sai, M.S.S., Krishna, A.B., Ganthi, P., Kankanala, S.K., Tinnaluri, S. and Simhadri, V., 2023. Machine Learning Algorithms for Predicting the Loan Status. Journal of Survey in Fisheries Sciences, 10(2S), pp.3677-3685.
Know more about UniqueSubmission’s other writing services:
