Sayam Kumar's Projects
Successfully developed an encoder-decoder based sequence to sequence (Seq2Seq) model which can summarize the entire text of an Indian news summary into a short paragraph with limited number of words.
In this project, I have analyzed Amazon sales records, defined KPIs(Key Performance Indicators) and established meaningful relationships between them for deriving useful statistical insights.
This repository contains all the Python files, dashboards and reports associated with the IBM Data Science Capstone project.
Successfully established a machine learning model using PySpark which can accurately classify whether a bank customer will churn or not up to an accuracy of more than 86% on the test set.
Successfully established a clustering model which can categorize the customers of a renowned Indian bank into several distinct groups, based on their behavior patterns and demographic details.
Successfully established a deep learning model which can accurately predict whether a woman's face is beautiful or average.
Successfully developed a machine learning model which can classify whether an email is spam or ham.
Successfully established a machine learning regression model which can estimate the gross Black Friday sales for a particular customer, based on a distinct set of related and meaningful features, to a fair level of accuracy.
Successfully established a deep learning model which can detect the license number plates of cars.
Successfully developed a Linear Regression Model which can be used to predict the price of cars based on a set of independent variables.
Successfully established a deep learning model which can precisely classify a human being as a child or an adult.
Successfully developed a machine learning model which can accurately predict whether a firm will become bankrupt or not, depending on various features such as net value growth rate, borrowing dependency, cash/total assets, etc.
This repository covers all the concepts taught in renowned Udemy instructor Josa Portilla's course on Computer Vision.
Successfully developed a machine learning model which can accurately predict the strength of cement based on various features such as blast furnace slag, water, coarse aggregate, etc.
Successfully designed and developed a system which analyzes and compares multiple PDF documents, specifically identifying and highlighting their differences.
Successfully developed a machine learning model which can accurately predict up to 100% accuracy whether a credit card application of a given applicant would be approved or not, based on several demographic features such as applicant age, total income, marital status, total years of work experience, etc.
Established a machine learning model which can predict whether a credit card transaction is fraudulent or not to a significant level of accuracy.
Successfully developed a machine learning model which can accurately classify the credit score of a customer based on his/her's basic bank details and a lot of other credit-related features.
Successfully created a regression model for performing predictions on the net area yield of any particular crop.
Successfully established a machine learning model which can predict whether any given customer currently utilizing the products and services offered by a company will churn at anytime in the future or not, depending upon a set of unique features/characteristics pertaining to that specific individual, to a great level of accuracy.
Successfully developed a chatbot model which can provide accurate and concise responses to a wide variety of customer queries regarding the services offered by a particular company as well as general topics.
Successfully fine-tuned a pretrained DistilBERT transformer model that can classify social media text data into one of 4 cyberbullying labels i.e. ethnicity/race, gender/sexual, religion and not cyberbullying with a remarkable accuracy of 99%.
Working with databases through DB API using Python. Mainly, I worked with a database instance created at IBM DB2 cloud, created and loaded several datasets within it and issued SQL queries for accessing and manipulating data of each provided dataset.
Successfully established a machine learning model for detecting whether a given tweet is about a real disaster or not.
Successfully established a deep learning model which can accurately predict the drowsiness state of an individual and thereby alert a driver who is in a drowsy state for preventing fatal accidents.
Successfully established a machine learning model that can accurately classify an e-commerce product into one of four categories, namely "Books", "Clothing & Accessories", "Household" and "Electronics", based on the product's description.
Successfully developed a fine-tuned BERT transformer model which can effectively perform emotion classification on any given piece of texts to identify a suitable human emotion based on semantic meaning of the text.
Successfully established a machine learning model which can accurately predict whether an employee of a given company will leave it in the impending future or not, based on several employee details and employment metrics.
Complete Analysis of English Premier League data of 20 years.