Business Commons^™

Identifying At-Risk Clients For Xyz Packaging, Co., Eduardo Carlos Cantu Medellin, Mihir Parikh, Christopher Graves, Brendon Jones

SMU Data Science Review

We present a multi-algorithmic modeling approach for the identification of at-risk customers for XYZ Packaging Inc. We define at-risk customers as those having declining seasonally adjusted gross income forecasts which are a strong indicator of impending customer churn. Customer retention is an area of interest regardless of industry but is especially vital in commodity-based low margin industries. We employ traditional Autoregressive Integrated Moving Average (ARIMA) and Anomaly Detection algorithms for discriminating changes in customer revenue patterns. Ultimately, we identify a meaningful proportion of clients whose forward-looking quarterly demand can be predicted within an actionable degree of accuracy.

Big-Data Talent Analytics In The Public Sector: A Promotion And Firing Model Of Employees At Federal Agencies, Rabih Neouchi

Operations Research and Engineering Management Theses and Dissertations

Talent analytics is a relatively new area of focus to researchers working in analytics and data science. Talent Analytics has the potential to help companies make many informed critical decisions around talent acquisition, promotion and retention. This work investigates data science to predict “shiny star” employees in the U.S. public sector, defined as top-notch performers over the years of a given time span. Its scope falls within talent analytics, also called people analytics, a relatively new research area.

We clean a data set made available by the U.S. Office of Personnel Management (OPM) and present two models to predict the …

Optimize The Effectiveness Of Recruiting Campaigns, Ryan A. Talk, Lakshmi Bobbillapati, Marshall Coyle

SMU Data Science Review

Abstract. Recruiting marketing plays an important role in the talent acquisition strategy today. To find the best candidates, companies make substantial investments through numerous recruiting agencies, job boards, and internal systems such as Indeed, LinkedIn, Monster, Talent Communities. In this paper we obtained a company’s LinkedIn Job Posting data to try to predict the number of visits they will receive for each job posting based on the time of the year it is posted. We compare AR(1), AR(2), AR(52), MA(1), and ARMA(1, 1) time series methods to a baseline of a persistence model. We found that out of these 5 …

Leveraging Reviews To Improve User Experience, Anthony Schams, Iram Bakhtiar, Cristina Stanley

SMU Data Science Review

In this paper, we will explore and present a method of finding characteristics of a restaurant using its reviews through machine learning algorithms. We begin by building models to predict the ratings of individual reviews using text and categorical features. This is to examine the efficacy of the algorithms to the task. Both XGBoost and logistic regression will be examined. With these models, our goal is then to identify key phrases in reviews that are correlated with positive and negative experience. Our analysis makes use of review data publicly made available by Yelp. Key bigrams extracted were non-specific to the …