Business Analytics Commons^™

Predicting House Prices Using Machine Learning, Pejal Rath, Robert Slater

SMU Data Science Review

This study explores the use of Machine Learning methods to predict housing prices, a problem of significant interest in real estate economics, and data science. Traditional hedonic pricing models have long been used to evaluate the impact of housing attributes on property values, but they often lack the flexibility to capture nonlinear relationships and complex feature interactions. Recent advancements in regression based and Machine Learning approaches provide promising alternatives that may improve prediction of accuracy and market insights. This research will investigate how models such as linear regression, random forest, and gradient boosting can be applied to publicly available housing …

Application Of Open-Source Small Large Language Models For Finance Report Analysis, Tue Vu, Mark Austin, Marcel Tuijn

SMU Data Science Review

The rapid integration of generative AI in finance introduces both opportunities and challenges, particularly when analyzing sensitive data such as Securities and Exchange Commission (SEC) filings. This study investigates the use of open-source Small Large Language Models (SLLMs), deployed locally through the Ollama and LangChain frameworks, combined with Retrieval-Augmented Generation (RAG) for extracting financial insights relevant to index performance and reporting quality. Two key objectives guide this work: (1) benchmarking multiple open-source SLLMs for sentiment analysis, multiple-choice reasoning, and financial question answering, and (2) assessing the feasibility of locally deployed SLLMs for domain-specific financial queries. A standardized set of 50 …

Enhancing Animal Shelter Operations With Time Series And Machine Learning, Sakava L. Kiv, Donald L. Anderson, Shivam Negi, Jacquelyn Cheun

SMU Data Science Review

Enhancing animal shelter operations through machine learning involves employing a variety of advanced techniques aimed at increasing efficiency, promoting animal welfare, and optimizing resource allocation. This paper explores predictive analytics for adoption rates using regression models to estimate the likelihood of adoption based on historical data, encompassing variables such as breed, health status, and previous adoption trends. Additionally, classification algorithms are utilized to categorize animals by adoption probability, facilitating better resources and marketing prioritization. Clustering algorithms are employed to group animals according to behavior patterns and/or physical health, enabling tailored medical care and enrichment activities that improve their mental and …

Enhancing Customer Support Operations Through Gpt & Q-Learning: A Model Study, Adam Alidra, Bob O'Brien, Dalton Young

SMU Data Science Review

Abstract. “Growth strategies that are purpose-led, customer-centric, experience-driven, data/AI-enabled, and technology-scaled require new mindsets…” (Cornfield, 2021). What can we take from this? Business growth and customer experience are inextricably tied together. Therefore, thriving, as an organization, is dependent on reimagining enterprise operations through modern, scalable data and AI technologies. Our study aims to enhance support operations with emerging AI capabilities, including OpenAI’s LLM models, built on self-attention mechanism transformer architecture, and tailored for business needs through prompt engineering. Our research uses Markov Decision Process and the Q-learning algorithm to evaluate synthetically created support incidents. Through this set of methods, our …

Analysis Of First-Time Completion In The Field Service Environment, Gavin Rick, Scott Englerth, Marc Carter, Hayley Horn

SMU Data Science Review

First-time completion is an important measure of service quality and efficiency in the field service industry. Customers call upon field service providers to repair their equipment in a timely manner so it can be put back into service for their business demands. Responsiveness can be measured through first-time completion and is defined as completing the repair on the first visit of a service call. This research is exploring the first-time completion in the forklift service industry. This research found the primary factors that impact first-time completion percentage in this industry include parts on hand, parts backorder process, technician experience, and …

A Machine Learning Approach To Revenue Generation Within The Professional Hair Care Industry, Alexander K. Sepenu, Linda Eliasen

SMU Data Science Review

The cosmetic and beauty industry continues to grow and evolve to satisfy its patrons. In the United States, the industry is heavily science-driven, innovative, and fast-paced, suggesting that to remain productive and profitable, companies must seek smart alternatives to their current modus operandi or risk losing out on this multi-billion-dollar industry to fierce competition. In this paper, the authors seek to utilize machine learning models such as clustering and regression to improve the efficiency of current sales and customer segmentation models to help HairCo (pseudonym for confidentiality), a professional hair products manufacturer, strategize their marketing and sales efforts for revenue …

Enhanced Data Science Methods For Freight Optimization At Kelly-Moore Paints, Lance Dacy, Reannan Mcdaniel, Shawn Jung

SMU Data Science Review

Kelly-Moore Paints is a paint manufacturing company founded in San Carlos, California in 1946 by William Kelly and William Moore. It has stores located in California, Texas, Oklahoma, and Nevada. They currently own 11 42’ trailers, contract 4 distinct drivers, and service 44 stores Monday-Thursday from its Texas Distribution and Manufacturing Center in Hurst, TX. Given that transportation costs are typically the highest in the supply chain costs, this study will employ data science techniques to ensure the transportation routing, store ordering mechanism, and trailer utilization are at the best efficiency possible given the current ordering patters of the stores. …

Price Optimization For Revenue Maximization At Scale, Nikhil Gupta, Massimiliano Moro, Kailey A. Ayala, Bivin Sadler

SMU Data Science Review

This study presents a novel approach to price optimization in order to maximize revenue for the distribution market of non-perishable products. Data analysis techniques such as association mining, statistical modeling, machine learning, and an automated machine learning platform are used to forecast the demand for products considering the impact of pricing. The techniques used allow for accurate modeling of the customer’s buying patterns including cross effects such as cannibalization and the halo effect. This study uses data from 2013 to 2019 for Super Premium Whiskey from a large distributor of alcoholic beverages. The expected demand and the ideal pricing strategy …

Automated Interactive 3d Geospatial Data Assimilation, Formatting And Visualization System For Development Of Subsurface Conceptual Site Models, Aaron Cattley, Gavin Hudgeons, Bruce Lee

SMU Data Science Review

The natural evolution of the collection and storage of sub- surface data in Texas has resulted in the current state where data for certain resources, such as water resources, have not been assimilated with state oil and gas and injection data in a meaningful way that allows for rapid understanding and data analysis for a physical land site. The consequences that result due to data from different spheres not being in sync are often duplication of work being performed but not in a consistent manner. However, the reality is that the infrastructure and impacts of these sectors are deeply intertwined. …

Qlime-A Quadratic Local Interpretable Model-Agnostic Explanation Approach, Steven Bramhall, Hayley Horn, Michael Tieu, Nibhrat Lohia

SMU Data Science Review

In this paper, we introduce a proof of concept that addresses the assumption and limitation of linear local boundaries by Local Interpretable Model-Agnostic Explanations (LIME), a popular technique used to add interpretability and explainability to black box models. LIME is a versatile explainer capable of handling different types of data and models. At the local level, LIME creates a linear relationship for a given prediction through generated sample points to present feature importance. We redefine the linear relationships presented by LIME as quadratic relationships and expand its flexibility in non-linear cases and improve the accuracy of feature interpretations. We coin …

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.

Generalized Relay Network Design And Collaborative Dispatching In Truckload Transportation, Amin Ziaeifar

Operations Research and Engineering Management Theses and Dissertations

The truckload industry faces a serious problem of high driver shortage and turnover rate which is typically around 100\%. Among the major causes of this problem are extended on-the-road times where drivers handle several truckload pickup and deliveries successively; non-regular schedules and get-home rates; and low utilization of drivers dedicated time. These are by-and-large consequences of the driver-to-load dispatching method, which is based on point-to-point dispatching or direct shipment from origin-to-destination, commonly employed in the industry. In this dissertation, we consider an alternative dispatching method that necessitates careful design of an underlying network. In this scheme, a truckload on its …

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 …

Demand Forecasting: An Open-Source Approach, Murtada Shubbar, Jared Smith

SMU Data Science Review

In this paper, we compare demand forecasting methods used by the supply chain department at Bilports to open-source forecasting methods. The design and implementation of the open-source forecasting system also attempts to use several external datasets such as consumer sentiment, housing permit starts, and weather to improve prediction quality. Additionally, the performance of the forecast is evaluated by the reduction of shipment lead times from China, the company’s primary vendor. The objective of our paper is to improve Bilports’s forecasting capabilities. The primary motivation of this paper is to increase forecasting accuracy and identify the weaknesses of the methods used …

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 …

Improving Vix Futures Forecasts Using Machine Learning Methods, James Hosker, Slobodan Djurdjevic, Hieu Nguyen, Robert Slater

SMU Data Science Review

The problem of forecasting market volatility is a difficult task for most fund managers. Volatility forecasts are used for risk management, alpha (risk) trading, and the reduction of trading friction. Improving the forecasts of future market volatility assists fund managers in adding or reducing risk in their portfolios as well as in increasing hedges to protect their portfolios in anticipation of a market sell-off event. Our analysis compares three existing financial models that forecast future market volatility using the Chicago Board Options Exchange Volatility Index (VIX) to six machine/deep learning supervised regression methods. This analysis determines which models provide best …

Yelp’S Review Filtering Algorithm, Yao Yao, Ivelin Angelov, Jack Rasmus-Vorrath, Mooyoung Lee, Daniel W. Engels

SMU Data Science Review

In this paper, we present an analysis of features influencing Yelp's proprietary review filtering algorithm. Classifying or misclassifying reviews as recommended or non-recommended affects average ratings, consumer decisions, and ultimately, business revenue. Our analysis involves systematically sampling and scraping Yelp restaurant reviews. Features are extracted from review metadata and engineered from metrics and scores generated using text classifiers and sentiment analysis. The coefficients of a multivariate logistic regression model were interpreted as quantifications of the relative importance of features in classifying reviews as recommended or non-recommended. The model classified review recommendations with an accuracy of 78%. We found that reviews …

The Resource Allocation Optimization Problem For Cloud Computing Environments, Victor Yim, Colin Fernandes

SMU Data Science Review

In this paper, we present the use of optimization models to evaluate how to best allocate cloud computing resources to minimize cost and time to generate analysis. We look at cloud platform providers Amazon Web Services, Google Cloud and Microsoft Azure on their product offering. We selected 18 machine configuration instances among these providers and analyze the pricing structure of the different configuration. Using a support vector machine analysis written in python, performance data was gathered on these instances to compare time and cost on various data sizes. Using this result, we build models that allow us to select the …