Ayush KaulThakur College of Engineering and Technology, MumbaiSharad BharadiaThakur College of Engineering and Technology, Mumbai Prince SinhaThakur College of Engineering and Technology, Mumbai.Say no to plagiarism. Get a tailor-made essay on “Why Violent Video Games Should Not Be Banned”? Get Original Essay In this modern age, where the world is moving towards automation, so it is necessary to automate the answer evaluation system. Currently, online answer evaluation is available for MCQ based questions, so the theoretical answer evaluation is hectic for the checker. The teacher manually checks the answer and authorizes the grades. The current system requires more manpower and time to evaluate the response. This project is an application based on answer evaluation using machine learning. The project is developed specially to reduce the consumption of labor and time. Because in manual response evaluation, labor and time consumption are much more. Furthermore, in the manual system, it is possible that the marks assigned to the same two answers are different. This application system provides automatic evaluation of the answer based on the keyword provided to the application in the form of a data set by the user, which will ensure equal distribution of marks and reduce time and labor -work. Keywords: OCR, backpropagation algorithm, ReLU, ANN Introduction (title 1) Manual evaluation of responses is a very tedious task. Manual verification is a very time-consuming process and is also labor-intensive. Also, the paper checker is not able to give equal marks. So our system will evaluate the answer based on a keyword and manpower will also be saved. Then just scan the paper, based on the keyword in the answer, the system will provide the marks for the question based on the data set present. Moreover, with this system, the error in assessing marks for a particular question will be reduced. So our system will evaluate the answer based on a keyword and manpower will also be saved. Just scan the paper, then the system will split the answer using OCR[3], based on the keyword in the answer, the system will provide the marks to the question based on the set of data present [4]. There is a need for such an application which will provide easy evaluation of the answer and can provide eligible marks. Also, this app will help various colleges, universities and coaching institutes to evaluate the answer in less time and with less manpower. Checking answers requires great concentration for a long time, which often leads to mistakes. Automating this task will increase the efficiency of response evaluation at scale. After a brief discussion, it was understood that the answer sheet is evaluated keeping in mind certain keywords that the moderators look for to find the answer while evaluating an answer. Our proposed algorithm will require keywords as inputs. These keywords will be provided by the subject matter expert. The proposed algorithm will match these keywords with the detected words which are extracted from the answer sheet using a supervised learning algorithm. The training phase of the model will require a handwritten dataset for English language alphabets. These datasets are available online in different formats to be used to train the model. The machine learning model used in our proposed algorithmis made up of neural networks with several hidden layers. The model calculates the error using a backpropagation algorithm. The network weights are updated in the opposite direction to partial error differentiation relative to the neuron's weighted input in a particular layer. The activation function used for the model is ReLU (rectified linear unit) which is calculated as: f (x)=max(0,x)Here, the variable x is an input to the function. Our proposed algorithm will also consider the response length as a response evaluation parameter. The ideal response length will be taken into account by the teacher. Research Paper “An Approach to Assess Subjective Questions for Online Examination System” by Sheeba Praveen, Assistant Professor, Department of CSE, Integral University, Lucknow, UP, India. In recent years, we have noticed that a number of semi-governmental government exams have been moved online, for example [IBPS Common Written Examination (CWE)]. This system or any other similar system has advantages in terms of saving resources. However, we observed that these systems only answer multiple choice questions and there is no provision to extend these systems to subjective questions. Our goal is to design an algorithm for automatic evaluation of a single sentence descriptive response. The article presents an approach to check the student/learner's level of learning, by evaluating their descriptive exam answer sheets. Representing the descriptive response in graphic form and comparing it with the standard response are the key steps in our approach. B Vanni, M. shyni and R. Deepalakshmi, “High precision optical character recognition algorithms using ANN training array” in Proc. 2014 IEEE International Conference on Circuit, Power, and Computing Technologies (ICCPCT), International Conference 2014. Optical character recognition refers to the process of translating handwritten or printed text into a format understood by machines for editing, searching and indexing purposes. Current OCR performance illustrates and explains real errors and imaging defects in recognition with illustrated examples. This paper aims to create an application interface for OCR using artificial neural network as a backend to achieve high recognition rate. The proposed algorithm using the neural network concept provides high accuracy rate in character recognition. The proposed approach is implemented and tested on an isolated character database consisting of English characters, numbers and special keyboard characters. Proposed Methodology This project is an application for automated response evaluation using the corresponding keyword from a dataset based on a machine learning algorithm. There are some apps available but they are different and use a different methodology. Some available applications only evaluate MCQs (multiple choice questions) and not the subjective question[1]. To use this app, just scan the answer to that question, then the system will split the answer keyword using OCR [3]. Based on the keywords written in the answer and the keywords in the dataset, the app will provide scores between 1 and 5. Steps to evaluate the answer. Provide an answer sheet to the system in jpeg (.jpg) format providing the key words, maximum marks and minimum length required for the answer. The system will separate the words from the given answer the given words will be stored in a .csv file the length of the 0=.