Nov 2021 – Dec 2021 · 1 mo · New Delhi, Delhi, India · Remote

• Task1-Iris Flower Classification:
• Performed in-depth Exploratory Data Analysis (EDA) and handled preprocessing tasks such as missing values and feature scaling.
• Trained classification models (Logistic Regression, Decision Tree) to predict Iris species, with visual insights using scatter plots and confusion matrices.
• Achieved 95%+ accuracy, demonstrating strong grasp of supervised learning, model evaluation, and data visualization.
• Task2-Stock Market Prediction and Forecasting Using Stacked LSTM:
• Developed a deep learning model using Stacked LSTM networks to forecast stock prices based on historical data.
• Preprocessed time-series data using scaling and windowing techniques, then trained and evaluated the model with TensorFlow/Keras.
• Achieved accurate trend forecasting and minimised RMSE, demonstrating practical skills in time-series modelling and neural networks.
• Task3-Decision Tree Classification:
• Built a supervised machine learning model using DecisionTreeClassifier to predict student performance based on study hours.
• Applied data preprocessing, train-test split, and model evaluation using accuracy score and visualization tools.
• Achieved 95–100% prediction accuracy; effectively visualized decision paths and feature splits to interpret model logic.
• Tools used: Python, Numpy, Pandas, Scikit-learn, MS Excel

Oct 2021 – Nov 2021 · 1 mo · New Delhi, Delhi, India · Remote

• Task1: Exploratory Data Analysis - Retail:
• Conducted comprehensive exploratory data analysis (EDA) on a global retail dataset to extract actionable insights across sales, profit, discount, and customer behavior.
• Analyzed sales and profitability trends across regions, states, and categories, identifying key drivers of performance.
• Discovered that Western and Eastern US regions had the highest sales, but some sub-categories (like Tables and Bookcases) showed negative profit margins despite high sales volume.
• Used correlation matrices, bar plots, heatmaps, and boxplots to examine relationships between discount and profit, revealing that excessive discounting beyond 30% leads to substantial losses.
• Highlighted top-performing segments (e.g., Technology in California) and underperforming ones (e.g., Furniture in Texas), offering strategic suggestions for profit optimization.
• Task2: Prediction using Supervised ML:
• Predicted a student’s percentage score based on the number of hours studied using simple linear regression, a supervised machine learning technique.
• Performed exploratory data analysis (EDA) to understand the relationship between hours studied and scores, using visualizations like scatter plots.
• Preprocessed the data by splitting it into training and testing sets.
• Trained a linear regression model to predict scores based on study hours.
• Evaluated the model using metrics such as Mean Absolute Error (MAE) and R-squared.
• Predicted the score for a student studying 9.25 hours per day, as specified in the task.
• built a linear regression model that accurately predicted student scores, achieving a high R-squared value (typically around 0.95), demonstrating proficiency in supervised learning and regression analysis.
• Tools Used: Python, pandas, NumPy, seaborn, matplotlib.

Sep 2021 – Nov 2021 · 2 mos · India · Remote

• Completed the Financial Markets Experience Program (FMEP), a 2-month virtual internship focused on equity trading and research, enhancing skills in portfolio management and financial analysis.
• Managed a virtual stock portfolio on a real-time BSE 500 platform, optimizing returns through strategic stock selection and weekly performance analysis using Python and Excel.
• Authored an equity research report on a selected Indian company/sector, delivering actionable investment recommendations based on fundamental analysis.
• Conducted technical analysis using indicators like RSI and Moving Averages, identifying trading opportunities through Python-based visualizations.