• Dr. Ritesh Kumar

Data-driven polymer research is reshaping how macromolecules are conceived, synthesized, and deployed by linking curated, FAIR data to physics-informed machine learning and autonomous experimentation. Computational approaches are now an important part of polymer chemistry. They let scientists guess a material's bulk properties based on its molecular structure. The goal is to figure out which structural elements control certain behaviours so that new materials can be designed in a logical way. But this procedure is made more difficult by a number of real-world problems, such as short datasets, changing molecular weights, and complicated polymer topologies. As a result, generic computational models are typically not very useful unless they are heavily customised. To get over these problems, chemists and data scientists need to work together in a way that helps both groups. The chemist's job is to help define the problem by using their knowledge of the field, and the data scientist's job is to make models work in the unique chemical context. This research seeks to bridge the multidisciplinary divide by tackling issues related to data quality and emphasising how recent scientific progress has enhanced data accessibility. We look at how materials are used in the field, from anticipating how well they will work to designing them for drug delivery. Finally, we talk about how important it is to share data (FAIR Data Principles) and how powerful it is to combine conventional polymer theory with new, data-driven insights.

Data Scientists, FAIR Principles, Polymer Chemistry, Data, Drug Delivery.

"Data-Driven Approaches in Polymer Research", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.e68-e76, November-2025, Available :http://www.jetir.org/papers/JETIR2511410.pdf

"Data-Driven Approaches in Polymer Research", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppe68-e76, November-2025, Available at : http://www.jetir.org/papers/JETIR2511410.pdf