Schizophrenia is a severe psychiatric disorder associated with delusions and hallucinations, which results in extremely disorganized behavior and cognitive impairments in patients, whose count is nearing more than 1 Million in India. In addition to that, patients suffering with schizophrenia are at the higher side of suicide risk, since their lifetime suicidal rate increases by approximately 10%. Further, many cases of schizophrenia remain untreated till today, due to critical factors such as failure to diagnose, social stigma and self-denial. However, in the literature, lot of research studies are carried out toward Schizophrenia diagnosis by employing complex investigation strategies such as Magnetic Resonance Imaging (MRI), Electroencephalography (EEG) and gene classifications. Due to these issues, the early prediction of preliminary-level Schizophrenia symptoms is urgently needed, which significantly helps in further treatment and also slows down the progression of disease to higher stages. Based on these aspects, this research study proposes a new framework, which predicts the preliminary-level Schizophrenia symptoms from the clinical || demographical factors by employing different machine learning algorithms such as Logistic Regression. Experimental evaluations conducted on patient datasets demonstrate the efficiency of the proposed framework in terms of Precision, Recall, F1-score, Accuracy and confusion matrices, respectively.