Python, EDA, ML, DL, Neural Networks, Computer Vision, NLP.
Python, Django, Cloud, Docker, Linux, Flask, HTML, CSS.
Pandas, Numpy, Matplotlib, Seaborn, PowerBI, MySQL.
Data Science Project Intern
iNeuron.ai
CAE Intern
Simulation Lab.
Subject Matter Expert
Chegg India Pvt. Ltd.
Graduate Enginner Trainee
Endurance Technologies Pvt. Ltd..
B.Tech Mechanical Engineering
Greater Noida Institute of Technology, 68.68%
Higher Secondary
Woodbine Modern School, 79.8%
Secondary School Certificate
Woodbine Modern School, 9.6 CGPA
Built an app where we use images of the infected leaves of the crop to detect the type of disease using Computer Vision. Used Keras for image preprocessing, augmentation, rescaling. Used CNN architecture for reading image and training the model. Used Keras Tuner and employed different optimizers like SGD, Mini-Batch SGD, RMSProp and Adam an finally used Adam for model building with highest accuracy of 82%.
This is my NLP project where i have used huggingface pretrained model api in order to summarize the text content.I have build end to end website using flask api where user can easily get high quality text summaries they required.Iam also trying to build my own custom tranformers for training my nlp models.
Book recommendation system based on collaborative filtering using the name of the book and ratings given by users. Employed cosine similarity metric to measure user-item & item-item similarities using Pivot table. Built an end-to-end application using Flask and deployed using Docker and GitHub Actions as CI/CD pipeline on Heroku Cloud.
Built a Flight Fare prediction system using Supervised Learning and Regression models on flight dataset from Indian Airlines. Employed feature engineering techniques like One-Hot Encoding and Label Encoding to deal with categorical data. Employed Random Forest Regressor with Hyperparameter tuning to achieve an R2-score of 81%. Deployed an end-to-end application to Heroku cloud developed using Flask.
Built a clustering model using K-means to identify major customer segments. Applied feature engineering to obtain new features such as Recency, Frequency, Monetary and RFM score for getting more details about the customer. Obtained optimal number of clusters using Silhouette Analysis, Elbow method and visual inspection of Dendrogram from Hierarchical clustering.
Used Django for the Web App Development. Keeping track of your daily activities is an impossible task when you have so much to do and there is not enough time to think about what is needed to be done. This learning log is a web application to do just the right thing. Using this you can perform and track you activities for present and make future plans and time them according to your comfort. Using this app is easy. You just have to login and you are good to go. The best part is your data is never shared with anyone. Your data is only available to you and will remain until you decide to remove it.