Akash Kumar Singh Email & Phone Number

Gurugram, Haryana, India

Bengaluru, Karnataka, India

During my internship at IIM Ranchi, my main focus was on performing topic modeling and various data analysis techniques on web-scrapped data of web series genres to extract meaningful insights.Initially data cleaning and pre-processing was performed and transforming the data into a suitable structure for further analysis. I generated WordClouds for different N-grams to identify the most common words and gain insights into the key themes and topics within the web series genres. Furthermore, I utilized the correlation coefficient on bigrams to create a knowledge graph using the NetworkX library to visualize the relationships and dependencies between different elements in the dataset.To uncover the topics present in the web series data, I applied advanced topic modeling techniques such as Latent Dirichlet Allocation (LDA) and Contextualized Topic Modelling (CTM). By implementing them and fine-tuning the models, I successfully identified and extracted the main topics within the web series genres. I used pyLDAvis to visualize the discovered topics.In addition to topic modeling, I also performed multilabel regression on a separate dataset designed for regression tasks, using various models such as XGB Regressor, Feed Forward Neural Networks (NN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (Bi-LSTM). To evaluate the performance of the models, I used Root Mean Squared Error (RMSE). The XGB Regressor consistently outperformed the other models in terms of accuracy and predictive power.Moreover, I addressed missing values in different datasets by employing imputation techniques like K-Nearest Neighbors (KNN) and MissForest to minimize the potential bias and errors that could arise from incomplete datasets.

Master Of Science (Research): M.S.(R), Artificial Intelligence

Bachelor Of Science - Bs, Data Science And Engineering

12, Pcm, 96.2

10, 9.4