MEGHANA C N

Assistant Professor

Qualification Details

• B. E (Computer Science and Engineering)
• M. Tech (Computer Science)

Professional Experience

• Learnvista | Freelance Data Scientist Associate | December 2022 to December 2023

1. Project title – “Empowering Financial Security: Detecting Fraudulent Transactions” Objective – To develop a Machine Learning model to detect potentially fraudulent transactions based on the transaction’s information. Tools and techniques used – Logistic Regression, Decision Tree Description – The extensive EDA process revealed that the dataset was imbalanced, and hence under-sampling method was used to overcome the problem. Then the LR model was built as a reference model and to further improve accuracy Decision Tree was built, which resulted in a F1-score of 1 for both training and test data.
2. Project title – “Predicting Rate of Interest using Advanced Machine Learning Techniques and Predictive Analysis” Objective – To build a Machine Learning Model for predicting the rate of interest for the loan using information of applicant and loan itself Tools and techniques used – Linear Regression, PCA Description – By the iterative process of cleaning the data, removing outliers and feature engineering. improved the performance of an existing regression model by decreasing the error rate from 13.9% to 10.7%

• Nokia Solutions and Networks | Student Trainee| July 2019 to June 2020

1. Project title – “Indoor Localization using Trilateration and Fingerprinting” Objective – The main objective of the project is to locate users in an indoor environment. Tools and techniques used – Linear Regression, k-Nearest Neighbor, Trilateration, Fingerprinting Description – Built two predictive machine learning models. Linear Regression was used to predict the distance between user and the Access Points. The output was fed to the Trilateration location engine to locate the user. In the Fingerprinting technique all the RSSI values and the location details was stored in a fingerprint database. Whenever a new user was traced, the k-NN model was used to match the nearest location of the user from the database.
2. Wi-Fi DHCP NAT feature testing: Testing DHCP and NAT features by capturing packets using Wireshark
3. Customer Document verification: Rigorous manual testing of Customer Document
4. Access Point performance testing: Tested the Access Point performance using IXVeriWave software
5. Designing lab setups (5G and Airphone): Drawing Lab diagrams using MS Visio and bringing up lab setups
6. Script writing : Wrote python scripts which helped in testing process

Certifications

• ‘Python for Data Science’ from Learnbay
• ‘Statistics and Machine Learning for Data Science’ from Learnbay

MOOC/ ARPIT/ SWAYAM certifications

• Completed “Introduction to Machine Learning” from AICTE

FDP/ Workshop attended

• Participated in ATAL approved Faculty Development Program on “Data Sciences”

Research area of Interest

Machine learning, Data Science