Data Analytics Specialist Transforms e-Commerce and Banking with Advanced Data Science With over 14 years of experience in data science, Sundriyal leverages advanced machine learning models and analytical frameworks to solve some of the most complex problems in driving product profitability, customer engagement, digital transformation and financial P&L forecasting.

Data has emerged as the new currency, powering critical decisions, shaping strategic initiatives, and driving significant business outcomes. Few understand the intricacies of harnessing this data more profoundly than Aniket Sundriyal, a data analytics specialist whose work spans over a decade across banking and ecommerce industries.

With over 14 years of experience in data science, Sundriyal has carved out a significant role for himself in the industry. He leverages advanced machine learning models and analytical frameworks to solve some of the most complex problems in driving product profitability, customer engagement, digital transformation and financial P&L forecasting.

Bridging Data Science and Business Outcomes

Aniket Sundriyal's professional journey began with a B. Tech in Electronics and Telecommunication Engineering from the National Institute of Technology Raipur, India. Early in his career, Sundriyal worked in significant analytics consulting firms like Mu Sigma and EXL services. As a senior analytics manager, Sundriyal led data-driven initiatives for a large U.S. financial institution. There, one of his focus areas was to develop econometric forecasting models in compliance with regulatory standards. Sundriyal's component-level forecasting improved prediction accuracy and raised the standard for capital planning, bolstering financial resilience across the industry.

"The key to effective data science is understanding both the technical possibilities and the business needs," he explains. "In the banking sector, we used data not just to understand customer behavior but to improve overall business performance through targeted, data-driven interventions."

In 2020, Sundriyal transitioned to Amazon's Woot, where he applied his expertise to solve complex e-commerce problems through data science. His one-product-view approach replaced the traditional aggregated data-based approach, setting a new industry benchmark by enabling more precise decision-making and boosting profitability.

Maximising E-Commerce Profitability with Intelligent Enterprise Reporting

At Woot, Aniket Sundriyal encountered the challenge of optimizing profitability in a highly competitive daily deals environment. Offering products at the lowest price often put pressure on profitability, especially when the product sourcing team lacked detailed data for informed decision-making. Recognizing the need for an intelligent solution, Sundriyal aimed to empower the sourcing team to make proactive pricing decisions, ensuring both customer satisfaction and strong financial performance.

"Optimizing profitability requires analyzing data at the most granular level—product by product—so we can make more precise decisions", he says. "Automated intelligence systems allow us to achieve this, empowering teams to react faster and make decisions that improve both financial outcomes and customer satisfaction."

Sundriyal developed an enterprise-grade solution that revolutionized profitability analysis at Woot by enhancing both efficiency and granularity with product-level insights. He designed a robust data architecture that automated the collection of all profitability components at the product level. Building on this, he created a dashboard that delivered actionable insights to key business stakeholders in areas such as pricing, shipping, and product returns, significantly improving profitability.

Sundriyal's one-product-view approach moved beyond traditional aggregated data, setting a new industry standard. By focusing on granular insights, it made decision-making easier, more effective, and accurate, driving profitability and encouraging wider adoption of detailed product-level analysis in e-commerce.

Ensuring Financial Stability with Advanced Forecasting Models

Sundriyal's contributions to the financial sector extended beyond digital transformation. As part of the Federal Reserve's Comprehensive Capital Analysis and Review (CCAR) process, which assesses the capital adequacy of major U.S. banks to ensure they can withstand economic downturns, a leading U.S. bank faced rejection of its capital plan due to flaws in its revenue forecasting models. Sundriyal was brought in to create advanced statistical models capable of forecasting credit card balances and revenue across five distinct macroeconomic scenarios.

"The challenge was to create models that could accurately predict revenue in both normal and adverse economic conditions," he recalls. "We used a combination of autoregressive models and business heuristics to forecast granular components of balances and revenue, while ensuring compliance with regulatory requirements."

Sundriyal deconstructed balances and revenue into granular components, developing autoregressive models for each. This approach enabled him to capture the diverse effects of economic scenario changes on individual components, significantly enhancing forecast accuracy. He conducted rigorous statistical analyses, ensuring the models met the strict standards of regulators and the financial institution's model governance team.

His work ultimately helped secure approval for the institution's capital plan and set a new benchmark for capital adequacy planning, reinforcing bank's long-term stability amidst economic uncertainty. Sundriyal's component-level forecasting framework introduced a new way for financial institutions to refine their predictions by focusing on key drivers. This approach enhances accuracy and adaptability, setting a higher standard for capital planning and strengthening overall financial resilience.

A Vision for Data-Driven Business

Sundriyal's work exemplifies data science's growing importance in e-commerce and banking. By applying data science to drive product profitability, and financial forecasting, he has demonstrated the immense potential of using data to drive business outcomes.

He remains focused on pushing the boundaries of what data science can achieve. His projects form part of a larger vision for data-driven industry decision-making. His work serves as a blueprint for how data science can solve today's challenges while paving the way for future growth and stability in the digital economy.

"The future of business is data-driven," Aniket Sundriyal says. "We're just scratching the surface of what's possible, and I'm determined to continue exploring how data can transform industries."