Exclusive interview with Naveed Ahmed Janvekar: Senior Data Scientist at Amazon

Naveed Ahmed Janvekar is a Senior Data Scientist working at Amazon in the United States. It works to address fraud and abuse issues on the platform that affects millions of Amazon customers in the United States and other parts of the world using machine learning and deep learning. . He has over 7 years of expertise in the field of Machine Learning, which includes Classification Algorithms, Clustering Algorithms, Graph Modeling, BERT, to name a few. It uses machine learning and deep learning to solve multifaceted problems. He holds a master’s degree in information science from the University of Texas at Dallas, where he graduated at the top of his class and was awarded as a Distinguished Researcher and inducted into the prestigious International Honor Society Beta Gamma Sigma. He holds a Bachelor of Engineering degree in Electronics and Communications from India. He has worked with other influential companies such as Fidelity Investments and KPMG. In his current role, he researches the identification of new vectors of fraud and abuse on e-commerce platforms and uses active learning to improve the performance of the machine learning model.

Editor’s note: The opinions expressed in this article are solely those of Mr. Naveed Ahmed Janvekar and do not express the views or opinions of his employer.

Q1: Tell us about your journey in AI and data science so far. What factors influenced your decision to pursue a master’s degree and a career in the field of AI?

Naved: I currently work as a Senior Data Scientist at Amazon, working to improve the shopping experience for customers by detecting and preventing entities that are abusive or violate policies within the platform. My AI/ML journey started a little before I enrolled in the master’s program at UT Dallas. While working with Fidelity Investments in India, I was inspired by a few analysts who were using data to make impactful business decisions. This experience, along with my ambition to pursue higher education, led me to study information science with a specialization in machine learning. After graduating from UT Dallas, I worked with KPMG as a Business Intelligence developer working on building reporting applications. In 2017, I joined Amazon as a Business Analyst and worked my way up to Senior Data Scientist.

Q2: Tell us about your current role?

Naved: My current role as a Senior Data Scientist is to build strategic data science roadmap/projects to continuously improve the customer shopping experience. On a daily basis, I engage with various business stakeholders on various business issues and scientific peers to discuss the latest ML methodologies. Model building, experimentation, data mining and coding are practically part of the daily routine. Innovating on behalf of customers is a daily occurrence.

Q3: What are the biggest challenges as a Data Scientist?

Naved: I believe a significant challenge is getting the right type of data for exploration, model training, and/or insight generation. Often the available data may not be structured or even available in relational databases. There may be data quality issues, missing data, and features needed to train the model may not be readily available. Also, being able to design these features can be quite time-consuming and complex.

Another challenge with supervised machine learning models is the lack of availability of high-quality training datasets. By high quality, I mean aspects such as sufficient label volume, data quality, and class balance, to name a few. Sometimes creating a narrative and effective story of any analytics or data science solution for stakeholders can be difficult due to the complexity of the information. It’s something you get better at with time and constant engagement with business partners.

Q4: What is your opinion on machine learning in the area of ​​fraud and abuse prevention?

Naved: Machine learning contributes to the scalability and accuracy of fraud and abuse detection in a cost-effective way. For example: if one were to manually assess each transaction or entity as fraud or not, there is a good chance of catching all bad transactions or entities. But in today’s world, the scale of transactions and interactions is enormous, billions of transactions, millions of entities make it humanly unprofitable and possible to assess them all manually. By using machine learning, one can automate fraud detection as much as possible with high predictive power and lower costs.

Q5: What advice would you give to aspiring machine learning and data science candidates?

Naved: Data science is seen by many as a generalist role. Therefore, while having a deep knowledge of data science is important, my advice would be to also focus on deep knowledge of data science such as the mathematical details behind the algorithms. This will give you an edge over others in the field. Also, be good at storytelling, communicating information to business stakeholders, and building a narrative around your solutions. Participate in as many data science competitions as possible, get involved in publishing research papers, and find mentors early in your career.

Q6: Can you name any books, courses, or other resources that most influenced your thoughts?

Naved: My biggest influencer was Andrew Ng, an American computer scientist. He has courses on Coursera which are pretty good. Hands-On Machine Learning with Scikit-Learn by O’Reilly Media is also a good book. For improving programming skills, my choice is leetcode for python and SQL. Data incubator is good for scholarships and certifications.

Q7: What do you think of Marktechpost.com?

Naved: I came across Marktechpost in 2021 and have been following it ever since. I really like the kind of articles and content that is published by this publication. Most of the latest ML innovations are covered and very well summarized for quick reading. This club with the courses made available by Marktechpost makes it a great place for AI professionals to regularly engage with the platform.

Sean N. Ayres