Mastering Probability and Combinatorics

Hello, I'm Akhil, a Senior Data Scientist at PwC specializing in the Advisory Consulting practice with a focus on Data and Analytics.

My career journey has provided me with the opportunity to delve into various aspects of data analysis and modelling, particularly within the BFSI sector, where I've managed the full lifecycle of development and execution.

I possess a diverse skill set that includes data wrangling, feature engineering, algorithm development, and model implementation. My expertise lies in leveraging advanced data mining techniques, such as statistical analysis, hypothesis testing, regression analysis, and both unsupervised and supervised machine learning, to uncover valuable insights and drive data-informed decisions. I'm especially passionate about risk identification through decision models, and I've honed my skills in machine learning algorithms, data/text mining, and data visualization to tackle these challenges effectively.

Currently, I am deeply involved in an exciting Amazon cloud project, focusing on the end-to-end development of ETL processes. I write ETL code using PySpark/Spark SQL to extract data from S3 buckets, perform necessary transformations, and execute scripts via EMR services. The processed data is then loaded into Postgres SQL (RDS/Redshift) in full, incremental, and live modes. To streamline operations, I’ve automated this process by setting up jobs in Step Functions, which trigger EMR instances in a specified sequence and provide execution status notifications. These Step Functions are scheduled through EventBridge rules.

Moreover, I've extensively utilized AWS Glue to replicate source data from on-premises systems to raw-layer S3 buckets using AWS DMS services. One of my key strengths is understanding the intricacies of data and applying precise transformations to convert data from multiple tables into key-value pairs. I’ve also optimized stored procedures in Postgres SQL to efficiently perform second-level transformations, joining multiple tables and loading the data into final tables.

I am passionate about harnessing the power of data to generate actionable insights and improve business outcomes. If you share this passion or are interested in collaborating on data-driven projects, I would love to connect. Let’s explore the endless possibilities that data analytics can offer!