Chronic heart failure (CHF) is a long-term condition in which the heart fails to deliver perfusion to target tissues and organs, resulting in insufficient metabolic needs at physiological filling pressures. With a 2% annual increase, CHF prevalence is frightening. CHF affects developed countries, especially seniors. About 2% of the healthcare spending goes on CHF diagnosis and treatment. In 2018, the US spent 35 billion USD on CHF treatment, and forecasts show that these expenses will quadruple in a decade. An experienced clinician can diagnose HF by examining the patient and studying blood samples of heart failure biomarkers. Unfortunately, clinical deterioration usually signifies a fully developed CHF episode that will require hospitalization. Phonocardiography can identify heart sound alterations as heart failure worsens. This project uses cutting-edge machine learning and deep learning models to detect chronic heart failure in phonocardiography (PCG) data. This is done via an end-to-end average aggregate recording approach that uses machine learning and deep learning characteristics. The ChronicNet model was compared against ML and DL models.