Digital Data is growing exponentially as a result of day-to-day automation done by the technology, without any restriction to a particular domain and to any technique with which the data is being collected, stored and retrieved. The data thus generated is of many types, and is in different formats, for both the observed data or generated data. These data may be categorized as structured, unstructured or semi-structured and they require to be stored in suitable formats of databases so that when needed, meaningful data can be retrieved from stored data in the form of information or pattern or insights. 80% of these data is in unstructured format across all domains of applications and 90% of the data in the medical domain is in the unstructured format which needs to be processed properly for adding worth to data and further efficient decision making. The processed information when increases to huge amount requires to be mined for knowledge discovery and adding other characteristics to data that can help in analyzing the data and including the context of data. Earlier storage of data in DBMS required data to be retrieved through query language, i.e., through MySQL but this legacy system encountered limitations while dealing with large amount of data. The next system of data processing termed Data mining implemented different methods for storing, analyzing, processing large amount of data followed by data analysis. There are many application domains where we can use data analysis techniques for decision-making, gaining understanding and modelling objectives in business. Data analytics being the newest domain of research is providing avenues for dealing with large dimensional data sets having n number of different characteristics that generate the context for each and every content of data. Apart from all the other domains one of the major application domains is the medical domain as a huge amount of data is generated by its different entities in this domain like incoming and outgoing patients, non-medical staff, different observational data. The presented research work is in the medical domain specializing in the domain to infant and child health domain with an objective to study how data analytic techniques can be applied for the analysis of EAO (Early Age Obesity) which is a very important cause of diseases in their future life and hence is an important feature for disease prediction in infants and child. As clinical data is growing at an exponential rate, medical data requires proper management, storage, security along with privacy of the information. Big data provides the platform to explore the technology for clinical data and to provide better disease predictions as well as treatment options with the best suitable pathological procedure. The presented research work in its first phase included a comprehensive literature survey followed by a characterization of BMI (Body Mass Indexing) as a disorder occurring in physical appearances and trailing vulnerabilities for lifestyle-based fatal diseases among children that is one of the prime concerns nowadays globally. Being overweight as a child is one of the most prevalent causes of an unhealthy life, with the long-term negative effect of being predisposed to numerous serious lifestyle illnesses for children who become obese at a young age. Obesity in children can be detected using BMI, which is a body mass index calculated using a child’s age-specific vitals. Increased BMI due to increased body fat deposition is associated with young-onset obesity (EAO). Both the parental and child risk factors influence this early-age obesity. Current research literature does not include maternal and paternal prime factors influencing Early Childhood Obesity(EAO) which we have included in our research work. Child from 0–2 years of age has higher body weight due to parental BMI, their sedentary lifestyle, and gestational weight gain (GWG). 3–5 age groups have a higher association with both paternal and child factors. In our research work, we have taken into consideration the vitals of child disease with early age obesity as the primary parameter along with the influencing parental factors. Excess bodily fat deposition has been linked to early obesity. Analyze the impact of parental variables on child obesity using analytical data methodologies such as decision trees, random forests, OLS Regression, and the k-means algorithm, and propose how catastrophic it can be, as well as the procedures needed to prevent it. The ongoing research finds the possibility of generating predictive models from existing/logged data and using them for imputation. With higher model accuracy decision tree, Random forest, k-means algorithm followed by two major hypothesis z-test and OLS regression has been done. The current model is adopted for finding PtD(Prone to disease) clusters on the data set. Due to the continuous changes in lifestyle and intake habit of calorie, obesity is the main reason behind the occurrence of many fatal diseases during childhood as well as after age.