MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123071 A) filed by Malla Reddy (MR) Deemed to be University; Malla Reddy Vishwavidyapeeth; Malla Reddy University; Malla Reddy Engineering College For Women; and Malla Reddy College Of Engineering And Technology, Medchal-Malkajgiri, Telangana, on Dec. 6, 2025, for 'ai-powered strategic risk anticipation framework for hyper-dynamic markets.'
Inventor(s) include Mandala Sreenivas; Mr. Valle Shyam Kumar; Dr. Ekta Maini; Ms. Nagalakshmi Panchakatla; Dr. A. Eswar Reddy; and Dr. S. Udaya Bhaskar.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The given invention reveals an AI-Powered Strategic Risk Anticipation Framework (ASRAF), a new system that predicts and quantifies systemic risks in hyper-dynamic markets (i.e. decentralized finance, algorithmic trading, global supply chains) by integrating disparate, high-velocity streams of data through sophisticated machine learning. Conventional risk management techniques are based on backward-looking statistical models (e.g. Value-at-Risk, Monte Carlo simulations) under the assumption of stationary or slow-varying market conditions. This reactive model is deeply insufficient in the contemporary, algorithm based, worlds where dangers manifest and spread with almost instantaneous velocity throughout interconnected systems and are frequently unmanageable with cascading failures. The ASRAF circumvents this shortcoming by changing the emphasis of historical possibility to the present anticipation. The concept of the ASRAF lies in the Multi-Layer Attentional Fusion (MLAF) Engine. This engine consumes heterogeneous data streams, such as unstructured text (social media sentiment, news), transaction data at high frequency, and network topology data (inter-asset correlation, liquidity concentration). The MLAF Engine uses a multi-headed Transformer network architecture that is explicitly used to identify and measure weak-signal, non-linear relationships between these forms of data. Most importantly, the engine is conditioned to detect precursor clues, little, early-stage exceptions that have traditionally pre-empted events of systemic risk, which allows the system to produce predictive warnings much earlier than the conventional models. The product of the MLAF Engine is a Dynamic Systemic Risk Vector (DSRV). This vector gives a probabilistic prediction of risk in a variety of dimensions (e.g., liquidity risk, counterparty risk, policy risk) in short and medium-term horizon. The ASRAF subsequently runs a Context-Adaptive Strategy Generator (CASG) to translate the DSRV into mitigation strategies that take the form of actionable pre-emptive mitigation strategies. This may include the recommendation of immediate rebalancing of portfolio hedges, the raising of collateral levels with regard to particular counterparties or automatic throttling of exposure to particular market segments before the projected risk comes into effect. The ASRAF offers users the ability to shift their focus away of reactive risk containment and respond to increasing risks to a proactive strategic maneuverability through the provision of verifiable, future-oriented insights based on real-time data fusion. The ability guarantees excellent capital protection and business continuity in fast changing, high-stakes setting, defining a new pattern of advanced risk management structure."
Disclaimer: Curated by HT Syndication.
