My internship played a big role in my career

Naveed Ahmed Janvekar started his career as an engineer at Fidelity Investments and became a senior data scientist at Amazon. He has worked with technical teams from different sectors specialized in early detection of abuse, active learning and social networks. Naveed’s professional background includes conducting data science research, speaking at summits, and publishing data science articles on various platforms.

Analytics India Magazine reached out to Naveed to discuss their background in data science, the fraud prevention space, and the must-haves for success in the industry.

From Fidelity Investments to Amazon Data Science

A few of my colleagues at Fidelity Investments were working with data and providing insights for the company. I developed a fondness for data when I started keeping tabs on my monthly expenses by analyzing my transactions. The ability to present raw data into meaningful insights led me to pursue data science.

I decided to get the education needed to pursue a career in data science and enrolled at the University of Texas at Dallas for a Master of Information Science in Data Science. During my Masters, I did an internship at Nanigans, an ad-tech startup in Boston. After graduation, I worked at KPMG, and in 2017 I had the opportunity to work at Amazon in the Fraud and Abuse Prevention team.

Fraud prevention at Amazon

Currently, I work at Amazon as a Senior Data Scientist in the Abuse Prevention team, where I am responsible for implementing machine learning-based solutions to detect and prevent any entity violating policy on the platform. -form. I have spent a lot of time researching and inventing to effectively use data science/machine learning in abuse detection. Besides technical work, I spend time working with product managers, software developers, and senior executives on my organization’s data science/machine learning vision.

In general, the fraud and abuse prevention space is evolving, which means that malicious actors are constantly trying multiple ways to deceive or gain access to the platform to commit policy-breaking behavior. Common types of fraud that exist in the industry are stolen credit card fraud and account takeover. In both types, phishing is the common mode attack.

Additionally, organizations sometimes have to deal with chargeback issues to compensate victims of credit card fraud. Businesses can use data available at the account level at the time of fraud or account takeover to model fraud to predict future risk. Techniques as simple as maintaining a blacklist of stolen credit cards or suspicious IP addresses are also effective in combating these short-term problems. While organizations can implement sophisticated machine learning models to prevent and detect such attacks, the timing of detection becomes crucial; therefore, companies can focus on early detection of these attacks to minimize business impact or customer impact.

Good data science project

The biggest challenge is getting the right kind of data science projects with measurable impact. As data professionals, we can work on many projects, but what really sets you apart is the value that can be generated or the impact it can have on your customers. I have always prioritized projects that have created significant business impact and positive customer experience in my career. Before starting a data science/machine learning project, I spend a lot of time identifying a problem statement and measuring its estimated impact for my business or clients.

Traineeship

My internship played a big role in my career and gave me the opportunity to work on large datasets and generate insights. Often the datasets we work with at school or university might be clean, but in the real world the datasets can get really messy. During my internship, I struggled to get the right sets of data, put them together, and build a narrative around my findings. As part of my internship, I published articles such as Facebook Relevance Score: The Magic Number and Facebook Relevance Score: 3 Tactics to Boost Your Ad Effectiveness. The posts are the result of my work on the use of regression analysis on ad spend optimization.

Essential skills

Given the wide scope of a data scientist, great importance is placed on being a generalist. But having a good scientific understanding of the algorithms and the math behind them will give you an edge. Python knowledge, A/B testing skills, metrics development, ability to collaborate with cross-functional stakeholders are extremely important. Storytelling, building a narrative around your projects, good product intuition, the ability to communicate ideas are also key.

Constantly researching the latest technologies in data science, collaborating with peers on various open source projects, and attending conferences are ways to stay relevant in the field.

Sean N. Ayres