Introduction:

Transportations firms faces many problems. The expectations about transport are increasing day by to and expected to be comfortable and also it have qualities to deal with climate crisis and should be use as a substitute for personal transport. Germany for example aims to modify transport according to climates requirement and it aims to increase the passengers who will use public vehicles instead of private vehicles four times in 2030 as compared to 2010. This is only possible if there is well sewed strategy , fascinating appeal and investment . With advance technology of now a days can deal with these requirement also there is a need for the government for funding to accomplish this aim. For specifically accurate planning accurate data on the demand ,operational and optimization potential for passenger transport is important .There are already many design sand data available according to the demand the huge increase in data with the passage of time is conclusion of the digitalization of passenger transport or public transport in recent years. Tragically, there Is lack of compatible data and this is the major planning issues foe the firms planning for public transportations and transportation corporations are unable to utilizes all the adapt which is available . so to avoid all this mess and for the expansion of public transport it is important to apply data science management over the available data of public transport . We explain our methodical approach to identifying and realizing this potential in this paper. We describe our methods for using data from public transport and talk about the things we discovered.

In order to provide a solution or away towards data management in public transport that will result in a successful and effective way to apply data science application. We have outline some hurdles in applying these applications and prepare some solutions. Without any shadow of doubt I can say with these advancements public transport will play a vital element of mobility on to the road in future.

At First , we analyze different methods for collecting data for public transportation and classify data sources they are often accessible to transportation providers.. in section 2 we have covered data sources and associated techniques .After classifying we have proposed a summary for businesses address through data analysis. we have took interviews from the public vehicles representatives associations a and from different corporations designing software for vehicles using publicly about the use cases they have in thought about data and problems they are facing due to insufficient information.

In section # 3 we go over the use cases that we found as well as running script of methods that has been using in literature to address these kind of situations. So these parts or categorization will help to have a debate on the application of data science in public vehicles.IN the ongoing study we will able to find how data science use to see some use cases of transportation

In the section 4 and 5 we enlist the hurdles of the public transport features and its data cause for the use of data an machine learning. We talked about research topics future solutions and challenging which transportation firms will face . This study ended with a solution point and summary in section #6. There is a perspective that will act as a roadmap for accomplishing the aim of expansion of public transport.