In the present study flexural strength of coir fiber reinforced polyester composite is predicted by using Artificial Neural Network. Randomly oriented coir fibers of length 10 mm were used to cast 3 mm, 5 mm and 6 mm thick specimens with fiber volume fraction of 10%, 15%, 20% and 25% respectively. The flexure tests were conducted as per ASTM D7264. From the experimental results it is observed that the flexural strength increased up to 20% fiber volume fraction and then it decreased. Further flexural strength is found to increase with increase in the thickness of composite specimens also. Composite specimen of 5 mm thickness with 20% fiber volume fraction recorded the highest flexural strength of 141.042 MPa. An Artificial Neural Network is adopted with supervised training approach to fix the optimum weighted matrix. Predicted results of flexural strength are also presented. Both the experimental and predicted results of flexural strength depict the similar trend. The error between predicted and experimental results is less than 5.00%, hence Artificial Neural Network can be effectively adopted to prognosticate the flexural strength of coir fiber reinforced polyester matrix composites; which reduces the expensive manual involvement and its related errors during conduction of experimental programme. Artificial Neural Network results can be obtained quickly than the experimental results. © The Society for Experimental Mechanics, Inc. 2016.