
With my core training in Statistics and Biostatistics, my research focuses on the development of robust statistical methodology, with applications spanning precision oncology, high-dimensional multi-omic integration, and public health modeling.
For a complete bibliography, please refer to my Google Scholar profile, ResearchGate profile, or my CV.
💡 Note: Publications highlighted in teal represent first-authored works.
Filter by research topic (Methods selected by default). Publications are numbered chronologically, matching my CV.
- 17. Zheng, Y., Cheng, C., Cao, Y., Cruz, G., Zhang, Y., Paturu, R., Mahapatra, S., Hu, J., Mannan, R., Karaburk, H., Bhattacharyya, R., ... & Qiao, Y. (2026). A stress-adaptive lipid kinase axis defines metabolic vulnerabilities in neuroendocrine prostate cancer. Cancer Cell, online now.
- 16. Cao, Y., Cheng, C., Yin, Y., Yee, S. N., Zheng, Y., Mahapatra, S., Paturu, R., Coleski, A., VanAken, S., Yang, F., Pakkan, R., Zhao, Y., Bhattacharyya, R., ... & Chinnaiyan, A. (2026). Targeting the ferritinophagy-lysosome axis as a therapeutic vulnerability in gastroenteropancreatic neuroendocrine tumors. Cell Reports Medicine, 7(4), 102695.
- 15. Luo, J., Chen, Z., Qiao, Y., Tien, J., Young, E., Mannan, R., Mahapatra, S., Bhattacharyya, R., ... & Chinnaiyan, A. (2025). Targeting histone H2B acetylated enhanceosomes via p300/CBP degradation in prostate cancer. Nature Genetics, 57, 2468 - 2481.
- 14. Cheng, C., Hu, J., Mannan, R., He, T., Bhattacharyya, R., Magnuson, B., ... & Chinnaiyan, A. (2025). Targeting PIKfyve-driven lipid homeostasis as a metabolic vulnerability in pancreatic cancer. Nature, 642(8068), 776 - 784.
- 12. Kundu, R., Datta, J., Ray, D., Mishra, S., Bhattacharyya, R., Zimmermann, L., & Mukherjee, B. (2023). Comparative impact assessment of COVID-19 policy interventions in five South Asian countries using reported and estimated unreported death counts during 2020 - 2021. PLOS Global Public Health, 3(12), e0002063.
- 9. Salvatore, M., Purkayastha, S., Ganapathi, L., Bhattacharyya, R., Kundu, R., Zimmermann, L., ... & Mukherjee, B. (2022). Lessons from SARS-CoV-2 in India: A data-driven framework for pandemic resilience. Science Advances, 8(24), eabp8621.
- 7. Purkayastha, S., Bhattacharyya, R., Bhaduri, R., Kundu, R., Gu, X., Salvatore, M., ... & Mukherjee, B. (2021). A comparison of five epidemiological models for transmission of SARS-CoV-2 in India. BMC Infectious Diseases, 21(1), 1 - 23.
- 5. Ray, D., Bhattacharyya, R., & Mukherjee, B. (2021). Discussion on “The timing and effectiveness of implementing mild interventions of COVID-19 in large industrial regions via a synthetic control method” by Tian et al. Statistics and Its Interface, 14(1), 25 - 28.
- 4. Salvatore, M., Basu, D., Ray, D., Kleinsasser, M., Purkayastha, S., Bhattacharyya, R., & Mukherjee, B. (2020). Comprehensive public health evaluation of lockdown as a non-pharmaceutical intervention on COVID-19 spread in India: National trends masking state-level variations. BMJ Open, 10(12), e041778.
- 3. Ray, D., Salvatore, M., Bhattacharyya, R., Wang, L., Du, J., Mohammed, S., ... & Mukherjee, B. (2020). Predictions, role of interventions and effects of a historic national lockdown in India’s response to the COVID-19 pandemic: Data science call to arms. Harvard Data Science Review, 2020(Suppl 1).
- 1. Liu, Q., Ha, M. J., Bhattacharyya, R., Garmire, L., & Baladandayuthapani, V. (2020, January). Network-based matching of patients and targeted therapies for precision oncology. In Pacific Symposium on Biocomputing (Vol. 25, No. 2020, pp. 623 - 634).
Selected industrial projects applying core statistical methodology and machine learning models to large-scale ads auctions, platform economics, and predictive user behavior. Click on each project to expand descriptions.
📊 Large-Scale Auction Diagnostics & Bidding Optimization
- Bidding Diagnostics Infrastructure: Engineered large-scale data processing pipelines to ingest, deduplicate, and analyze billions of daily auction logs. Developed custom database schemas to measure campaign budget pacing and bidding inefficiencies.
- Bidding Recommendation Scaling: Authored technical requirements to optimize Target CPM (Cost-Per-Thousand) bidding recommendations for complex, flighted advertising campaigns. This resolved a critical system limitation, expanding recommendation coverage to unlock $10M+ in annualized advertiser spend and $100M+ in budget headroom.
- Product Integration: Led cross-functional alignment with software engineering and UI teams to surface pipeline diagnostics as visual budget warnings directly in the advertiser-facing Google Ads console.
📈 Causal Revenue Modeling & Counterfactual Pricing Estimation
- Causal Proxy Modeling: Designed a mathematically bounded causal proxy using short-term revenue signals to replace inflated advertiser value estimates, successfully correcting for selection and survival biases in platform-wide counterfactual pricing models.
- Pricing Experimentation Operations: Assumed full technical setup, engineering operations, and statistical analysis for global subscription pricing experiments, implementing robust variance estimation and bootstrap workflows.
- Statistical Decision Support: Owned the statistical narrative and presented revenue-foregone analyses to senior leadership. Conducted confidence interval width sensitivity analyses across 100+ global markets to secure alignment on platform pricing rollouts.
🔮 Predictive Online-to-Offline (O2O) Campaign Modeling
- 0-to-1 Statistical Architecture: Led a greenfield machine learning initiative to predict campaign-level conversion rates (pCVR) for online-to-offline actions, establishing the data collection, tracking, and pipeline architecture from scratch.
- Robust Multi-Stage Modeling: Designed multi-stage models combining relative outcome differences, predictive conversion components, and inverse-bid proxies to manage heavy-tailed outliers and zero-inflation in sparse campaign metrics.
- Error Evaluation Metrics: Implemented customized error metrics to evaluate revenue models against large outliers, ensuring that large, high-volume campaigns do not skew model evaluation.
Upcoming Presentations
- International Indian Statistical Association (IISA) Conference (December 26 - December 30, 2026 | Banaras Hindu University, Varanasi, India)