Unmesh Mali

Unmesh Mali

Week 33, 2021

Thanks to SF’s homelessness problems (shattered glass everywhere), I am needing to fix flat tires on my bike almost every week. I didn’t have time to fix my bike’s flat tire so I borrowed Sarvesh’s bike to commute this week.

Work ★ ★ ☆ ☆ ☆

This was a slow week at Sunverge Energy. I was working from home on Wednesday and Friday. Well, not exactly home. I was in San Rafael supporting a medical treatment of my roommate. Working from San Rafael was a pleasant experience. I got to take calls and do work from the clinic’s waiting room half the time and from a Starbucks for the other half. Latte, Almond croissant, and data analysis. For the next week, I need to complete a task related to openADR. And I am also going to make a case to my boss to allow me to contribute to software development. The probability of me getting to work with software development is low but it is worth a try.

Projects ★ ★ ★ ★ ☆

Machine Learning Bootcamp

The week was all about deploying ML models. We deployed ML models on AWS Elastic Beanstalk using the CLI. There were multiple assignments on PySpark, Dash which I thought were pretty cool. All about parallel computation. We signed up for the community edition of Databricks which allowed the use of 1 cluster. Databricks is a one-stop shop for all data needs. We used it individually which defeats the purpose since it allows for collaboration. About the capstone project: Me and Tiziano have completed the model testing and tuning phase. If you don’t know, we are trying to identify fraudulent activity from a bank’s transaction database. We researched our way into using Unsupervised Anomaly Detection . The challenge with anomaly detection is that you cannot measure the performance of the model. There are no metrics. I see it more of a helper function. It can give you a lot interesting pattern in your data but then you have to meet the model in the middle and take the investigation further. That’s exactly what we are thinking of doing now – just identify interesting patterns in the data and investigate further with a different model. My task for the next week is to complete the flask app and deploy it on AWS EB. Looking forward.

CEEW – Sustainable Mobility Research Assistant

Great news to share – I got a 3-months extension on my internship. I did a decent job with the last assignment that I got. I don’t have the next project yet. Abhinav (my manager at CEEW) gave me a list of project to do which I listed in the last blog (Week 31) but I found out later that they are all policy projects. I am thinking a lot of internet research and document writing with these projects which I am not looking forward to. I think I am going to skip on all of those and find a project with data analysis or machine learning. Fingers crossed. Let’s see how this internship shapes my career going forward.

Books ★ ★ ★ ☆ ☆

Ghost in the Wires: My Adventures as the World’s Most Wanted Hacker | Kevin Mitnick

I started this book last week. I took a sudden interest in cybersecurity after I deployed the CEEW app on my local machine and exposed it over the internet. My friend – Aditya who is completing his PhD in AI and cybersecurity advised me against exposing my local machine. But I did it anyway. After that, I thought it’ll be cool to find out what could have gone wrong with my little experiment. Hence my sudden interest in cybersecurity. This book is the autobiography of Kevin Mitnick who is a renowned hacker turned cybersecurity consultant. So far it is full of cunning tactics to hack telephone lines (1970s :P). It is clear that he is addicted to hacking and finds very difficult to stay away from the adventure. Harder the hacking the more he gets kick out of it once he solves it. What I am learning from the book is Kevin’s social engineering skills and his tenacity with a problem. I hope these skills rub off on me minus the hacking addiction.

Fitness ★ ★ ★ ☆ ☆