The project synopsis deals with the technique
of Data-Analytics which is becoming a very influential
tool for decision-making today.
Software data analytics is key for helping
stakeholders make decisions, and thus establishing a
measurement and data analysis program is a recognized
best practice within the software industry. However,
practical implementation of measurement programs and
analytics in industry is challenging. In this chapter, we
discuss real-world challenges that arise during the
implementation of a software measurement and analytics
program. We also report lessons learned for overcoming
these challenges and best practices for practical, effective
data analysis in industry.
The main objective of this work is to understand
data for decision making. The author here tries to select
those locations that are not already crowded with
restaurants within the region and have a greater
population by using various data science and analysis
techniques to reach their goal of selecting optimal
locations. The advantages of each area will be clearly
expressed so that the best possible final location can be
chosen by the stakeholders.
The Author initialized a crawler to scrape the data
about the areas of cities using Wikipedia web page and
the real-time data set. Python’s geocoder library with
ArcGIS as a geocode provider, to get the coordinates of
the neighborhoods. After which the author applies the
clustering algorithm, K-Means, on the data to cluster the
neighborhood based on general venue density and analyze
& compare the sets in each cluster to conclude the most
promising and optimal locations for each restaurant type.
Which is then filter out only the target restaurant of
interest in each neighborhood, to analyze within the
Integrated Development Environment(IDE), Machine Learning (ML), Application Programming Interface (API), Domain Specific Language (DSL), Representational State Transfer (REST).