There has been tremendous growth in the medical sector over the years due to the advancement of technology and an increase in health problems has been observed. Due to people's hectic and busy schedules, health problems have increased. But since almost everyone carries their smartphone with them lately, an Android healthcare application can prove to be very useful. The intention behind this project is to create an Android application that can be used by people to manage their health. This system will use decision trees algorithm for diabetes prediction. The user will have to answer a questionnaire which will consist of various parameters regarding the user's health. This application will consist of features such as ordering medicines, booking doctor's appointments, medications and diet reminders. Decision trees use a tree structure to build classification models. Divides a data set into smaller subsets. The leaf node represents a decision. Based on the feature values ​​of the instances, decision trees classify the instances. Each node represents a characteristic in a decision tree instance that needs to be classified, and each branch represents a value. Instance classification starts from the root node and is sorted based on feature values. Categorical and numeric data can be handled by decision trees. Say no to plagiarism. Get a tailor-made essay on "Why Violent Video Games Shouldn't Be Banned"? Get an Original Essay Data mining is the method of examining massive, pre-existing databases to generate new information. Diagnosing and predicting an individual's health is an important goal of this project. It can be achieved using advanced decision tree machine learning algorithms. An Android application is one of the easiest methods for a person to manage health due to the increasing use of smartphones. The application will consist of a series of questions that the user will have to answer. This will then use decision trees which is a data mining algorithm. This will then immediately predict the possibility of diabetes. Apart from this, the app will also include features like diet tracking where a user can monitor their diet and the app will send notifications or reminders about the same. Other features will be the provision of booking a visit to the doctor. The app will also allow the user to order medicines. In this proposed system, several factors such as gender, age, blood sugar level, cholesterol, hereditary diseases and many other factors are taken into consideration. This way you can find out whether the user is prone to diabetes or not. The main goal is to predict the onset of diabetes and monitor a person's health based on the answers given by the user to the questionnaire. Other features also include tracking your diet, booking a doctor's appointment, and ordering medications. Many prediction algorithms are used, but due to parameter consideration or inefficiency of the algorithm, the accuracy is not so high. Therefore, we are considering many parameters and also use C5 classifier algorithm which provides high accuracy. The rest is divided into 6 sections. In sections 2 and 3 the related work and proposed work are presented, the paper is structured. In section 4 the proposed methodology is presented and the details regarding the algorithm to be used are explained. In section 5 the conclusions were included and finally in section 6 the future work.Android application for health monitoring and diabetes prediction using data mining techniques [1], in this article the authors proposed a project that seeks to apply information and create an Android application that can be used by patients for management of their health problems and would allow them to have a good life. The applications also create a system to predict whether a person is at risk of developing the disease diabetes in the next 10 to 15 years. The system uses the questionnaire method using Naive Bayes Algorithm A Data Mining Approach for Prediction of Heart Disease Using Neural Networks [2], the authors proposed a heart disease prediction system (HDPS) developed using neural network. The HDPS system predicts the probability of a patient contracting heart disease. For prediction, the system uses blood pressure, gender and 14 medical parameters similar to cholesterol. Two more parameters, namely smoking and obesity, are added here for greater accuracy. The results showed that the neural network predicts heart disease with almost 100% accuracy. Disease Prediction System Using Data Mining Techniques [3] proposed a research paper using data mining for better disease prediction. It uses medical data mining techniques such as classification, association rule extraction, and implemented clustering to evaluate different types of heart-related problems. The investigation of machine learning algorithms for disease diagnostics [4] provides us with the comparative evaluation of different machine learning algorithms for the diagnosis of different diseases such as diabetes, heart disease, liver disease, dengue disease and hepatitis using l medical imaging. It brings attention to the suite of machine learning algorithms and tools used for analyzing diseases and making decisions accordingly. C5.0 algorithm for improved decision tree with feature selection and error reduction [5] compared to ID3, C4.5 and C5.0 with each other. Among all these classifiers C5.0 provides more accurate and efficient results. This research paper used C5.0 as the base classifier, so the proposed system will classify the result set with high accuracy and low memory usage. The feature selection technique assumes that the data contains many redundant features, and then removes those features that do not provide useful information in any context. This paper also uses the reduced error pruning technique, which is used to solve the decision tree overfitting problem. Decision trees can handle both classification and regression problems. Decision trees only require a data table with which they will directly build a classifier. On the other hand, Naive Bayes requires you to manually build a classification. If a lot of tabular data is provided, it will fail to choose the best features that can be used to classify. Therefore, for this application, diabetes prediction will be done using the decision tree of the C5 classifier. This application requires the user to answer a questionnaire that will be related to the patient's symptoms and habits. This will be taken as input and using the decision trees algorithm it will be possible to predict the possibility of diabetes. The application has a feature where the user can enter their diet. This app will monitor it and provide the required analysis. The medications consumed by the user will also be monitored. The user can also book a visit to the doctor using this app. The detailsof the appointment will be sent to the doctor. Below are the system modules:1. Prediction2. Diagnosis3. Diet plan4. Reminder and alarm e5. Ordering medicines. Whether the user is prone to diabetes or not will be accurately predicted by this system using prediction algorithm calculations. New users must register to create their respective accounts in the system. Access to the system is provided to the user via a login interface. The user can login using username and password on which the user will be directed to the home page of the system. The user can then enter data for diabetes prediction. We are mainly focusing on diabetes mellitus type. The user can also use additional features such as maintaining a diet, dosage reminder, calling for a doctor's appointment, etc. The prediction will be made using the decision tree of the C5 classifier. Below are the parameters that would be considered in the dataset for the prediction algorithm:1. Genre2. Age3. BMI4. Blood pressure5. Smoking6. Weeklyexercise7. Consumption of salty foods8. Alcohol consumption9. Work stress10. Family history of blood pressure/diabetes11. Pregnant (if female)12. Blood fat level13. Consumption of healthy foods14. Consumption of fatty foods Decision trees fall under the scope of supervised machine learning (which means we have to explain the input and output in the training data) where continuous splitting of the data takes place based on a certain condition/parameter . The tree has two entities, the leaves and the decision nodes. The end result is in the leaves. And decision nodes slice the data. Suppose we need to find out whether a person is healthy or unhealthy. We have parameters such as age, type of food intake and exercise time. Here we have a yes or no decision, this can be called a binary classification problem. The final output on the leaf would be healthy or unhealthy. There are two main types of decision trees. The above example is a binary type of classification (Yes/No), where the output is either healthy or unhealthy. But here the decision is variable, i.e. categorical, i.e. the output is continuous. Regression Trees (Continuous Data Types), Decision Tree Steps: Algorithm: Generate a decision tree from the training tuples of the data partition, D.Input: Given the partition, D, is a set of training tuples and the associated class labels; attribute list, a set of candidate attributes; The attribute selection method is a procedure for finding out whether the splitting criterion best splits tuples into individual classes. This criterion consists of a split attribute and, possibly, a split point or a split subset. Output: a decision tree. Algorithm: (1) create a node N; (2) if the tuple in D is all of the same class, C, then (3) returns N as the leaf node labeled with class C; (4) if the attribute list is empty then (5) returns N as the leaf node labeled with the majority class in D; (6) apply attribute selection method (D, attribute list) to find the “best” split criterion; (7) label node N with a split criterion; (8) if the split attribute has values discrete and multi-way subdivisions are allowed, then(9) attribute list attribute list - subdivision attribute;(10) for each result “j” of the subdivision criterion(11) let Dj be the set of data tuples in D that satisfies result j;(12) if Dj is empty then(13) attaches a leaf labeled with majority class in D to node N; (14) otherwise connect the node returned by Generate decision tree (Dj, attribute list) to node N; end for return N;C5.