Prasad Kulkarni

I am a Data Analytics professional with 5+ years of experience.

Azure Machine Learning Pipelines for Model Training

With AI becoming mainstream, automation of ML workflows is becoming critical. This includes automation of Training, Deployment and Inference of ML Models. These Machine...

Motivating DP-100: Designing and Implementing a Data Science Solution on Azure

Data Science has a come a long way. From Jupyter notebooks on a Data Scientists’ laptops, we have moved to complex ML workflows running in cloud infrastructure....

Explainable Machine Learning with Azure Machine Learning

In the previous two articles, we took a dive into Explainable Machine Learning. The first one dealt with LIME and SHAP for a supervised machine learning setting. The...

Machine Learning Interpretability for Isolation forest using SHAP

In our previous article, we covered Machine Learning interpretability with LIME and SHAP. We introduced the concept of global and local interpretability. Moreover, we...

An Introduction to Interpretable Machine Learning with LIME and SHAP

Introducing Interpretable Machine Learning and(or) Explainability Gone are the days when Machine Learning models were treated as black boxes. Therefore, as Machine...

Motivating Entity Resolution for Data Science

Why Entity Resolution? Data is the new oil. Thus, analytical models are the new combustion engines. A combustion engine functions efficiently with good fuel. Similarly,...

Fast data loading from Pandas Dataframe to Azure SQL Database

Writing pandas data frames to an Azure SQL database either requires you to use a cursor or the SQL Alchemy library(particularly, we use the to_sql function). However,...

Log Loss as a performance metric

Introduction to Log Loss Whenever we talk about performance metrics of the classification Machine Learning algorithms, the following names come to our mind: Accuracy...

An Introduction to Azure Synapse SQL

Evolution of Azure Synapse SQL Azure Synapse was previously known as Azure SQL Datawarehouse. With the re-branding to Synapse, Microsoft added many more layers on top of...

Python Dedupe Library : Machine Learning to De-Duplicate Data

In Information systems, the biggest challenge faced by organizations is the quality of data. Hence, unclean, messy, and missing data is a common headache across the...