Collaborated with a team to leverage Large Language Models (LLM) in developing an innovative Chatbot for interview preparation.
Engineered question generation and response validation using OpenAI, Google Palm and Cohere APIs
.
I implement three algorithms for anomaly detection; Isolation forest, Local Outlier Factor and SVM
Isolation forest gave the best accuracy (99.74) of all the three algorithms hence best for anomaly detection for this project.
I used NLP techniques like stemming & removal of stop words to preprocess the dataset for classification.
Implemented TFIDF and Count Vectorizer then applied multinomialNB & Passive aggressive algorithm to classify the given news
The goal of the project is to make forecasting on sales amount
I first visualize the data and make it stationary
I then plot the correlation and Autocorrelation charts followed by construction of ARIMA/seasonal ARIMA based on the data
.
The goal of this project was to predict the likely selling price of a car using features like current price & fuel type.
I applied a random forest regressor as the ML model since it had the best accuracy out of other regression models.
.
I use python do perform explanatory data analysis, feature engineering and feature selection.
The dataset used in this project is the house price prediction dataset from kaggle.
Utilized Power BI to create customer analysis dashboard
Transformed and processed data by using DAX and Excel to ensure data completeness and validity.