Road Traffic Accident (RTA) is a crucial matter that needs to be resolved, for it is one of the prime causes of fatality and injury. Therefore, methods of reducing the severity of an accident are of considerable concern to traffic authorities and of the public, in general. In Metro Manila, there were certain roads that are infamous for having high collision incidences, injuries and casualties. This study focused on the top three accident-prone roads with the highest recorded occurrences specifically EDSA, C-5 Road, and Commonwealth Avenue. The researchers applied Multinomial Logistic Regression to determine the significant factors linked to accident severity and to find the model that would be able to predict RTAs along the three major roads. The factors which substantially influence the response variable, accident severity (Fatal Injury, Non-Fatal Injury, and Damage to Property), were evaluated. The predictor variables were Month, Time, Accident Factor, Collision Type, Weather Condition, Gender, and Age. The data for these variables were collected from Metro Manila Accident Reporting and Analysis System (MMARAS) managed by the Road Safety Unit (RSU), a subunit of Metropolitan Manila Development Authority (MMDA) from the year 2014-2019.The purpose of this research is to propose a prediction model to prevent traffic congestion by predicting the occurrence of Road Traffic Accidents. This study will impart knowledge of the efficient flow of traffic and increased road safety. 
In the first major road, EDSA, the researchers were able to determine six (6) variables that were relative to accident severity. These are Month, Time, Type of Collision, Accident Factor, Gender and Age. The predictor variables found to be significant for EDSA were Accident Factor and Collision Type. The highest percentage of prediction probability for Damage to Property is from No Error Stated which resulted in Other Collision Types. 
In the second major road, C-5, the researchers were able to find out four (4) variables that were relative to accident severity, they were Month, Time, Accident Factor and Collision Type. The variables identified to be significant for C5-Road were Weather Condition, Collision Type and Time. The highest percentage of prediction probability is for Damage to Property from a Rear End Collision that happened during the Morning with Fair Weather conditions. 
The last major road that was analyzed was Commonwealth Avenue. There were four (4) variables associated with accident severity, they were Month, Time, Collision Type and Weather Condition. The third major road, Commonwealth Avenue, has the highest percentage of prediction probability for Damage to Property is from Multiple Collisions that happened during the Night with Fair Weather conditions. The researchers recommended that to be able to counter Road Traffic Accidents along EDSA, C-5 Road and Commonwealth Ave., the three (3) variables linked to accident severity were that should be closely monitored are: month, time and collision type. 

Keywords: road traffic accident, Multinomial Logistic Regression, accident severity, predictor,   collision type