Analysing the Relationship Between CSR and Financial Performance Using AI and Machine Learning Techniques

Corporate Social Responsibility (CSR) has arisen as a significant subject in contemporary business, with many organizations carrying out CSR techniques to fulfil partner assumptions and work on their standing. But since the monetary impacts of CSR drives are as yet indistinct, scholastics are investigating the way in which they connect with monetary execution. With regards to overseeing unpredictable, non-direct associations, conventional insightful procedures are restricted. New advancements in computerized reasoning (simulated intelligence) as well as AI (ML) give solid instruments to more exact examination of CSR and monetary execution. With an accentuation on anticipated exactness, cognizance, and reasonable consequences, this study investigates the manners by which man-made intelligence and ML approaches may be utilized to look at the association between monetary execution and CSR drives. In every industry, the Keras-trained MLP consistently yielded favourable results. The target of 900 epochs, or MLP (900), was used to train the MLP. It illustrates how training the same model over prolonged periods of time greatly improves performance. The LSTM model does not seem to generate better results, despite showcasing exceptional accuracy in natural language processing and long log security-related problems. As per the discoveries, artificial intelligence driven examination can give definite bits of knowledge into how corporate social responsibility (CSR) influences firm productivity, helping organizations in going with informed choices on their CSR strategies.