International Journal of Neutrosophic Science IJNS 2690-6805 2692-6148 10.54216/IJNS https://www.americaspg.com/journals/show/3188 2020 2020 Department of Economics and Management of Elabuga Institute, Kazan Federal University, Kazan, 420008, Russia K. K. Department of Management, Kuban State Agrarian University named after I.T. Trubilin, Krasnodar, 350044, Russia Rustem Shichiyakh Irina Gladysheva Department of Computer Science and Information Technology, School of Computing, Kalasalingam Academy of Research and Education, Krishnankoil, India M. Ilayaraja Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, 602105, India K. Shankar An interval neutrosophic set (INS) is an example of a NS, which is simplified from the theory of fuzzy set (FS), classical set, paradoxist set, intuitionistic FS, paraconsistent set, interval-valued FS, interval-valued intuitionistic FS, and tautological set. The association of an element to an INS is stated by 3 values such as t, i, and f. These values signify memberships of truth, indeterminacy, and false, correspondingly. Bankruptcy prediction is also called a corporate failure or bankruptcy prediction, which is a major focus in the area of finance and accounting, as the condition of a business is extremely substantial to its partners, shareholders, investors, creditors, even its suppliers, and buyers. Practitioners and researchers were reserved for emerging models and approaches to forecast the bankruptcy of companies more rapidly and precisely. With the excessive growth of contemporary information technology, it has developed to use machine learning (ML) or deep learning (DL) techniques to perform the prediction, from the preliminary study of economic statements. This study introduces an Optimized Bankruptcy Prediction using Feature Selection with m-Polar Neutrosophic Topological Spaces (OBPFS-MPNTS) method. The projected OBPFS-MPNTS system uses the parameter tuning and DL method to forecast the presence of bankruptcy. To achieve this, the OBPFS-MPNTS approach uses min-max normalization to convert input data into a uniform format. The OBPFS-MPNTS method begins with a grey wolf optimization (GWO) for selecting feature subsets. In addition, the OBPFS-MPNTS algorithm applies the m-polar neutrosophic topological space (MPNTS) system for bankruptcy prediction. To upsurge the performance of the MPNTS system, the whale optimizer algorithm (WOA) is employed. The experimentation outcome study of the OBPFS-MPNTS system is verified on a benchmark database and the outcomes pointed out the developments of the OBPFS-MPNTS algorithm over other current methodologies. 2025 2025 10.54216/IJNS.250225 https://www.americaspg.com/articleinfo/21/show/3188