Aman Pandey

Data Scientist

Bengaluru, Karnataka, India4 yrs 3 mos experience

Most Likely To SwitchAI Enabled

Key Highlights

Proficient in Machine Learning and Data Science.
Experience in Credit Risk Analytics and forecasting KPIs.
Strong analytical skills with a focus on data-driven decision making.

Stackforce AI infers this person is a Data Scientist with expertise in Machine Learning and Analytics within the SaaS industry.

Contact

Skills

Core Skills

Machine LearningData Science

Other Skills

A/B TestingA/B testsAI AgentsAnalytical SkillsAuto-ARIMABusiness AnalyticsC (Programming Language)C++CUPED algorithmCredit Risk AnalyticsDecomposed Hubers Regression ModelDynamic XGBoostEconomicsExperimentationFinance

About

Data Science | Machine Learning | Business Analytics | Python | MySQL | Tableau | Excel Have worked with Fittlyf as a Data Science Intern. I am an ambitious and self-driven professional and love making sense of data and numbers. I look forward to joining a collaborative, challenging, and growing workplace to utilize my skill set in a better and more productive way. Currently pursuing B.Tech in Biotechnology from IIT Guwahati.

Experience

Piramal capital & housing finance limited

Data Scientist

Jul 2023 – Present · 2 yrs 8 mos · Bengaluru, Karnataka, India · Hybrid

Working in Credit Risk Analytics; leveraging GenAI, NLP and Machine learning techniques to build scalable solutions

GenAINLPMachine learningCredit Risk AnalyticsMachine LearningData Science

Fittlyf

Data Science Intern

Jul 2022 – Oct 2022 · 3 mos

Built Time Series models to forecast KPIs like Qualified Prospects and Activations on region and traffic source level using Decomposed Hubers Regression Model (MAPE 27%), Auto-ARIMA (MAPE 20%) and Dynamic XGBoost(MAPE 15%) and devised growth strategies based on insights from the forecast.
Created a Proof of Concept for the usability of CUPED algorithm which is state-of-the-art variance reduction technique for A/B tests to propose it to engineers and higher leadership.

Time Series modelsDecomposed Hubers Regression ModelAuto-ARIMADynamic XGBoostCUPED algorithmA/B tests+2