Predictive Modeling and Big Data: PayPal Case Study Analysis

This case study analyzes PayPal's use of predictive modeling to understand consumer buying habits based on their location, shopping preferences, and internet browsing history. The assignment requires an analysis of how personal shopping and online browsing history are utilized for predictive analytics, examining the impact of predictive modeling on society, the economy, and privacy. The solution discusses PayPal's strategies, including the use of big data analytics, HBase, Hadoop technology, and analytical systems to combat fraud and deliver personalized advertisements. It highlights the benefits of predictive analytics for businesses, such as improved sales and demand forecasting, while also addressing the potential privacy concerns arising from the collection and analysis of consumer data. The study references the work of DeZyre and others to support the analysis and conclusions.

Running head: PREDICTIVE MODELLING 1
Analysis of Predictive Modeling: A Case Study of PayPal
Name
Institutional Affiliation

PREDICTIVE MODELING 2
The recent market capitalization ranks PayPal among the top 5 companies for payment.
Besides, PayPal has become common for online processing of payments over the web using
strategies like Data Science and Big Data Analytics in accessing the buying habits of customers
based on their location. The two strategies have been fruitful in enriching her costumers through
every day experiences. Merchants remain the real customers of PayPal though their customers
indirectly consume services of PayPal hence are customers as well. PayPal makes it easier and
comfortable for customers to shop. Besides, it achieves this by safely and securely processing the
payments of vendors and auction websites through cloud computing (DeZyre, 2016).
To achieve its ends, PayPal indulges in provision of improved capabilities in prediction
helping the merchants improve the experience of their customers. For example, a merchant like
Walmart can have the desire to efficiently market her products. In this case, PayPal through her
data scientists can create the list of target customers in a way that help with prediction hence the
success of the company. The data scientists use transactional data in predicting the purchasing
behavior and patterns of consumers realized by analyzing online data such as customers views,
location, and visited websites (DeZyre, 2016). According to DeZyre (2016), PayPal uses the
HBase and Hadoop technology; tying a knot with traditional databases with the Hadoop being
helpful in running exploratory queries while BI analysis helps with the identification of answers
through the uses of memories such as SAP HANA. However, Hadoop lacks advanced security.
To help fight fraud, the company identifies cases of fraud, relying mostly on the analytical
systems and technologies like spark which make use of human detectives, online caching, and
algorithms to combat fraud. Moreover, analyses of past payment also play a role in identifying
scam.

PREDICTIVE MODELING 3
In addition, PayPal uses advanced big data analytics in delivering personalized ads and
offers of a company. Today, there are numerous communications taking place on websites,
smartphones, and tablets whereby customers are enticed with offers and advertisements based on
location. Current shopping trends challenge advertisers and marketers in placing their ads. In this
case, PayPal leverages big data thus sending the data to several customers. Analysis of past
shopping trends helps connect merchants and customers thus saving on money as well as driving
the volumes of transactions. For example, PayPal has the information that customers who
undertake their shopping at a given depot are likely to enjoy their meals at the nearby Subway
thus sending those customers ads of the nearby Subway. PayPal is also vital in enriching the
experience of customers by providing insights from the conversations made by other customers
on the feeling and love of a given product (DeZrye, 2016) .
Being a consumer of online advertisement, there is a high tendency of my browsing and
shopping history being used for predictive analysis. Besides, reading of business ads aids the
possibilities of use of browsing history. Also, participation in various surveys also has higher
chances in the inclusion of views and opinion entered in these databases. As a consequence, the
economy will further grow owing to the modern marketing patterns which has reduced the globe
into a mere market place. Predictive analytics help companies gain popularity as well as saving
on money. It helps companies to forecast on the requirements thus improving on their sales. Also
it will improve demand, pricing, maintenance, and the discovery of new applications (LaRiviere,
McAfee, Rao, Narayanan, & Sun, 2016). However, the predictive capabilities have low chances
in promoting privacy of the customer such their tastes, preferences, locations, and buying habits
will be exposed while predictions are made.

PREDICTIVE MODELING 4
References
DeZyre. (2016, March 12). Big Data Use Cases: How PayPal leverages Big Data Analytics.
Retrieved from https://www.dezyre.com/article/big-data-use-cases-how-paypal-
leverages-big-data-analytics/231
LaRiviere, J., McAfee, P., Rao, J., Narayanan, V. K., & Sun, W. (2016, May 25). Where
Predictive Analytics Is Having the Biggest Impact. Retrieved from
https://hbr.org/2016/05/where-predictive-analytics-is-having-the-biggest-impact