Browsing by Author "Islam, Jahirul"

Now showing 1 - 5 of 5

An Ensemble Method for Predicting Loan Eligibility in Commercial Bank Using Machine Learning
(Daffodil International University, 23-01-29) Islam, Jahirul; Shakil, Kh.
In recent days in Bangladesh the number of loan applicants for loans in commercial banks are gradually increasing every year. Banking sectors always need a more accurate system for handling many issues. In order to select the right applicant who can return the loan amount within given time, the bank employees do a lot of analysis on the information provided by the applicant and based on the analysis give a prediction. But it is very difficult and time-consuming process for bank employees. To deal with this particular problem of predicting the right applicant for loan request we use the EDA (Exploratory Data Analysis) technique. A variety of machine learning models are used to aid in the task of loan prediction. A dataset made up of loan projections is used to assess the study. Data cleaning procedures were applied, such as deleting null columns, using the mean mode approach to fill in missing values, and converting categorical values to numeric format. We employ two different methods to provide the greatest outcomes from the feature selection process. Traditional machine learning models employ distinct training and testing processes for both features, which are derived from various feature selections. Bagging Classifier, out of all the models, has attained the highest level of accuracy (88.00%), as well as a high recall and F1 score. The method of univariate feature selection was used to achieve this. As a result, the results suggest that Bagging Classifier might do very well when it comes to the task of predicting loan defaults.
Financial Performance Analysis of Basic Bank Ltd
(Daffodil International University, 23-01-14) Islam, Jahirul
In recent years, Bangladesh's banking sector has grown quickly and significantly. not only in our country. Globalization, technological development, and a lack of authority have all contributed to the rapid change in the condition of banking. The banking industry in our country has changed as a result of this transformation, which has had a significant impact on the industry globally. The banks are now forced to engage in market competition with both domestic and foreign businesses. This is the reason I made the choice to successfully finish my banking internship program. Program for Internships a requirement for receiving a BBA from DIU. Intern BBA Program at DIU Throughout this internship plan, Students must write a report about the particular institution. I'm thrilled to be a part of the required program at Basic Bank Limited. I spent three months in Basic Bank Limited's College gate office. This internship is a full-time working endeavor for Basic Bank Limited and a means of studying the banking industry as a whole. I had to decide on a study area while I was there in order to do in-depth research and convey my findings in the report. After finishing the three-month internship program, I have written this report from this point of view. I greatly appreciate this performance and am hopeful that it will help me advance my future professional endeavors.
Geographic Inequalities and Determinants of Anaemia among Preeclamptic Women: A Cross-sectional Sample-based Study in Bangladesh
(Springer Nature, 2024-06-20) Ali, Ahasan; Islam, Jahirul; Paul, Ratna; Parvin, Shahinur; Chowdhury, Abu Taiub Mohammed Mohiuddin; Islam, Rafiqul; Siddique, Sharmina; Rahman, Atiqur; Tasnim, Sayeda Tamanna; Hasna, Suraiya
"Background Anaemia among preeclamptic (PE) women is a major undefined health issue in Bangladesh. This study explored the risk factors associated with anaemia and mapped the regional influences to understand the geographical inequalities. Methods Data from 180 respondents were prospectively collected from the Preeclampsia ward of Dhaka Medical College Hospital (DMCH), Bangladesh. Anaemia was defined as a blood haemoglobin level less than 11.0 g/dl. Preeclampsia was defined as systolic blood pressure (SBP) ≥ 140 mmHg and diastolic blood pressure (DBP) ≥ 90 mmHg with proteinuria. Factors associated with anaemia were explored using the chi-square test. Logistic regression (LR) was done to determine the level of association with the risk factors. Results Among the participants, 28.9% were identified as having early onset and 71.1% reported late onset of PE. 38.9% of the subjects were non-anaemic, whereas mild, moderate, and severe anaemia was found among 38.3%, 17.8%, and 5% of patients respectively. The following factors were identified; including age range 25–34 (OR: 0.169, p < 0.05), a lower education level (OR: 3.106, p < 0.05), service-holder mothers (OR: 0.604, p < 0.05), pregnancy interval of less than 24 months (OR: 4.646, p < 0.05), and gestational diabetes mellitus (OR: 2.702, p < 0.05). Dhaka district (IR: 1.46), Narayanganj district (IR: 1.11), and Munshiganj district (IR: 0.96) had the highest incidence rates. Conclusion Determinants of anaemia must be considered with importance. In the future, periodic follow-ups of anaemia should be scheduled with a health care program and prevent maternal fatality and fetus morbidity in patients with PE."
Optimizing Cervical Cancer Prediction, Harnessing the Power of Machine Learning for Early Diagnosis
(2024-07-10) Hasan, Mahadi; Islam, Jahirul; Al Mamun, Miraz; Mim, Afrin Akter; Sultana, Sharmin; Sabuj, Md Sanowar Hossain
Cervical cancer is one of the most widespread ovarian cancers in the world. It is linked up with multiple risk factors such as Sexually transmitted diseases, human papillomavirus and smoking. Death rate can be reduced if early diagnosis is possible. In addition if early prediction can be possible it will help greatly patients as well as doctors to give them proper treatment immodestly. Our study focuses on various machine learning algorithms to forecast early detection of cervical cancer. Dataset for this work has been collected from kaggle.com. The given dataset consists of various demographic and medical features related to an individual’s sexual and reproductive health. With proper tuning of parameters using cross-validation in the training set, the XGB Classifier achieves an accuracy of 98% and a ROC AUC of 99%.
Optimizing Cervical Cancer Prediction, Harnessing the Power of Machine Learning for Early Diagnosis
(IEEE, 2024-07-10) Hasan, Mahadi; Islam, Jahirul; Al Mamun, Miraz; Mim, Afrin Akter; Sultana, Sharmin; Sabuj, Md Sanowar Hossain
Cervical cancer is one of the most widespread ovarian cancers in the world. It is linked up with multiple risk factors such as Sexually transmitted diseases, human papillomavirus and smoking. Death rate can be reduced if early diagnosis is possible. In addition if early prediction can be possible it will help greatly patients as well as doctors to give them proper treatment immodestly. Our study focuses on various machine learning algorithms to forecast early detection of cervical cancer. Dataset for this work has been collected from kaggle.com. The given dataset consists of various demographic and medical features related to an individual’s sexual and reproductive health. With proper tuning of parameters using cross-validation in the training set, the XGB Classifier achieves an accuracy of 98% and a ROC AUC of 99%.