Prabhat Dixit Email & Phone Number

India

Bangalore Urban, Karnataka, India

Bangalore Urban, Karnataka, India

1. Maintaining sales reports for the contact center and dealer field sales, ensuring accuracy and reliability in the data presented.2. Interact closely with end-users, to understand their needs and address any concerns or bugs they encounter in the daily running reports promptly.3. Collaborated with cross-functional teams to implement enhancements or new features in the reports.4. Optimization and implementing solutions to streamline our digital subscription operations and enhance customer satisfaction.

Bangalore Urban, Karnataka, India

1) Interacting with Client and Business Stake Holder to discuss the requirements and managing the deliverables. 2) Working on Oracle to Hive migration to create data and reports as per business requirement. 3) Validate the data after conversion and do the analysis on top of it for different important features. 4) Derive strategic trends and insights and executive-level presentations.

1) Developed classification model using Multinomial NB, Logistic Regression, Decision trees and Random Forest to analyze the sentiments of the reviews given by the customer in the data and made useful conclusions in the form of visualizations.2) Implemented K-means and Hierarchical clustering on cuisines, cost , and timings to categorize 10K Restaurant names into 4 different clusters which was evaluated using Silhouette score and Elbow Method.3) Employed text preprocessing techniques such as text cleaning, stemming, stop-words removal, and performed vectorization of the final text column (extracting adjectives and verbs only) using TF IDF.4) Experimented with performance metrics for various models using TF IDF and Bag of words and found Logistic Regression as the best model with a f1-score of 84%.

1) To find the relationship between the features of mobile phone and its selling price also predict the price range of mobile phones.2) Developed classification models like Xgboost, Decision Tree, Random Forest and KNN model to predict mobile price range in the market based on technical specs and achieved a precision of 94% on test data, with KNN being the best model.3) Carried out feature engineering themed across screen dimensions, battery life, microprocessor strength, camera specifications, internal memory specs, and come up with the best performing features using ExtraTree Classifier and Chi-Square techniques.4) Identified key factors that affect the mobile price range using the important feature and those are ram, battery power, pixel height and width.

Mumbai Area, India

Pune Area, India