I have collected 300 Bangle sentences of 10 Domains such as Politics, Law & Order, Business & Economics, Education, Lifestyle, Culture, Sports, Health, Science & Technology and Others from Facebook. Then, i have annotated the text based on Subjectivity and Polarity, also validated the annotation with Inter-Annotator Agreement (IAA) too. Last but not the least, we have added other groups data and some open source data from Kaggle which amounts to over 8500 Bangle sentences to develop LSTM model for multi-class text classification.
Worked on the Skin Segmentation Data Set from UCI Machine Learning Repository which contains 245057 instances. The skin dataset is collected by randomly sampling B,G,R values from face images of various age groups. It is a classification problem to find whether a given instance is a skin or not. Firstly, i did some EDA(Exploratory data analysis). Then, i have applied 4 machine learning(KNN, Logistic regression, SVM, ANN) algorithm using scikit-learn and keras to solve this classification problem and compare the performance of the algorithms. The entire workflow contains various ML tasks like model creation, model evaluation(with Confusion matrix, ROC curve, Accuracy), hyperparameter tuning, model selection etc.
Commercial banks receive a lot of applications for credit cards. Many of them get rejected for many reasons, like high loan balances, low income levels, or too many inquiries on an individual's credit report, for example. Manually analyzing these applications is mundane, error-prone, and time-consuming (and time is money!). Luckily, this task can be automated with the power of machine learning and pretty much every commercial bank does so nowadays. In this project, you will build an automatic credit card approval predictor using machine learning techniques, just like the real banks do.
The dataset used in this project is the Credit Card Approval dataset from the UCI Machine Learning Repository.