Search for: All records

Twenty Second Annual Hawaii International Conference on Education 

Given the importance of online retailers in the market, forecasting sales has become one of the essential market strategic considerations. Modern Machine Learning tools help in forecasting sales for many online retailers. These models need refinement and automatization to increase efficiency and productivity. Suppose an automated function can be applied to capture historical data and execute forecasting models automatically; it will reduce the time and human resources for the company to manage the forecasting system. An automated data processing and forecasting model system offers the marketing department more flexible market sales forecasting. Proposed here is an automated weekly periodic sales forecasting system that integrates: the Extract-Transform-Load (ETL) data processing process and machine learning forecasting model and sends the outcomes as messages. For this study, the data is obtained for an online women's shoe retailer from three data sources (AWS Redshift, AWS S3, and Google Sheets). The system collects the sales data for 120 weeks, then passes it to an ETL process, and runs the machine learning forecasting model to forecast the sales of the retailer's products in the next week. The machine learning model is built using the random forest regressor. The top 25 products with the most popular forecasting results are selected and sent to the owner’s email for further market evaluation. The system is built as a Directed Acyclic Graph (DAG) using Python script on Apache Airflow. To facilitate the management of the system, the authors set up Apache Airflow in a Docker container. The whole process does not require human monitoring and management. If the project is executed on Airflow, it will notify the project owner to inspect the cause of any potential error.

 

Online advertising is a billion-dollar industry, with many companies choosing online websites and various social media platforms to promote their products. The primary concerns in online marketing are to optimize the performance of a digital advert, reach the right audience, and maximize revenue, which can be achieved by predicting the accurate probability of a given ad being clicked, called the Click-Through Rate. It is assumed that a high CTR depicts the ad reaching its target customers while a low CTR shows that it is not reaching its desired audience, which may constitute a low return on investment (ROI). We propose a data-science-driven approach to help businesses improve their internet advertising campaigns which involves building various machine learning models to accurately predict the CTR and selecting the best-performing model. To build our classification models, we use the Avazu dataset, publicly available on the Kaggle website. Having insights on this metric will allow companies to compete in real-time bidding, gauge how relevant their keywords are in search engine querying, and mitigate an unexpected loss in spending budget. The authors in this paper strive to use modern machine learning tools and techniques to improve the performance of predicting Click-Through Rate (CTR) in online advertisements and bring change to the industry.

 

Promoting equitable undergraduate engineering education is an overarching concern at many minority-serving institutions (MSI). In addition, historical analysis of student performance in lower-division math and engineering courses at one of the largest MSI revealed an achievement gap in performance between the underrepresented minority students and other students. Furthermore, critical analysis of underlying factors overwhelmingly suggests that academic intervention coupled with sociocultural intervention may be a possible solution to help address this problem. Academic and sociocultural intervention strategies were designed and implemented in lower-division math courses through the National Science Foundation-funded project, “Building Capacity: Advancing Student Success in Undergraduate Engineering and Computer Science (ASSURE-US).” These strategies involved application-based math courses targeted explicitly at undergraduate engineering students. Results of academic intervention strategies in the lower-division math courses at one of the largest MSI demonstrate mixed effectiveness. The results of the academic intervention in lower-division Calculus I (N=150) show that 36% of students reported that the intervention was helpful and helped them learn math, while 38% were neutral. Overall, students reported having difficulty connecting the projects with the mathematics being taught. Similarly, only 10% of students expressed satisfaction with the redesigned intervention modules implemented in Integral Calculus II (N=90), while 52% were neutral. The sociocultural interventions include activities facilitated through the Student-Teacher Interaction Council. These activities include motivational speakers, exam preparation and stress-relief workshop, campus resources and college financial planning workshops, peer advising and learning communities, summer research, and faculty development and support. Results of the sociocultural intervention strategies show that 39% of students reported that the ASSURE-US project helped them identify role models in their discipline, while 34% reported that the project helped them identify and connect to a mentor. Students also reported higher awareness of campus resources, including mental health resources and academic support, with 89% and 90% of students reporting fully or partial understanding of these resources. The academic and sociocultural interventions of the ASSURE-US project were initially designed for in-person, hands-on, project-based, and student-faculty-involved activities; however, due to the COVID-19 pandemic, many of these activities were reimagined and redesigned for virtual instruction. The outcomes of this project so far were significantly impacted by the pandemic. 

Promoting equitable undergraduate engineering education is an overarching concern at many minority-serving institutions (MSI). In addition, historical analysis of student performance in lower-division math and engineering courses at one of the largest MSI revealed an achievement gap in performance between the underrepresented minority students and other students. Furthermore, critical analysis of underlying factors overwhelmingly suggests that academic intervention coupled with sociocultural intervention may be a possible solution to help address this problem. Academic and sociocultural intervention strategies were designed and implemented in lower-division math courses through the National Science Foundation-funded project, “Building Capacity: Advancing Student Success in Undergraduate Engineering and Computer Science (ASSURE-US).” These strategies involved application-based math courses targeted explicitly at undergraduate engineering students. Results of academic intervention strategies in the lower-division math courses at one of the largest MSI demonstrate mixed effectiveness. The results of the academic intervention in lower-division Calculus I (N=150) show that 36% of students reported that the intervention was helpful and helped them learn math, while 38% were neutral. Overall, students reported having difficulty connecting the projects with the mathematics being taught. Similarly, only 10% of students expressed satisfaction with the redesigned intervention modules implemented in Integral Calculus II (N=90), while 52% were neutral. The sociocultural interventions include activities facilitated through the Student-Teacher Interaction Council. These activities include motivational speakers, exam preparation and stress-relief workshop, campus resources and college financial planning workshops, peer advising and learning communities, summer research, and faculty development and support. Results of the sociocultural intervention strategies show that 39% of students reported that the ASSURE-US project helped them identify role models in their discipline, while 34% reported that the project helped them identify and connect to a mentor. Students also reported higher awareness of campus resources, including mental health resources and academic support, with 89% and 90% of students reporting fully or partial understanding of these resources. The academic and sociocultural interventions of the ASSURE-US project were initially designed for in-person, hands-on, project-based, and student-faculty-involved activities; however, due to the COVID-19 pandemic, many of these activities were reimagined and redesigned for virtual instruction. The outcomes of this project so far were significantly impacted by the pandemic. 

United Nations recognized access to safe drinking water as a human right, yet many countries in the developing world lack access to potable water. Recurrent incidences of water-borne illnesses have a devastating effect on the morale and personal well-being of many people living in developing countries, contrasting the achievement of the UN’s objective. Qualitative and semi-quantitative approaches used for risk assessment are often ineffective, time-consuming, and do not discern the risk due to ingestion of unsafe drinking water at the global scale. This research utilizes a global dataset of drinking water facilities to evaluate the risks using a clustering approach. Extensive data analysis involving predetermined risk thresholds, the exceedance of which indicates the potential adverse risk. These risk-thresholds are based on the JMP Service Ladder, which effectively utilizes density-based spatial clustering of applications. Risk analysis of 132 datasets was conducted to designate the risk categories ranging from low, medium, and high-risk. Of the dataset analyzed, 90 areas were designated as a low-risk category while 42 were medium-risk. Overall, the clustering approach is an excellent tool to analyze a large dataset for risk assessment which will help the potential stakeholder, including the water utility manager, to assess the potential risk due to declining water quality quickly. Additionally, the clustering approach can be further harnessed for better data visualization, long-term performance evaluation of water utility, and real-time drinking water quality monitoring. 

In order to contextualize calculus, first-year engineering students take on a semester-long design project that grounds engineering design as an epistemic practice. The project is designed to motivate students to creatively and collaboratively apply mathematical modeling to design roller coasters. Students are asked to engage as engineers and respond to a hypothetical theme park that has solicited design proposals for a new roller coaster. Students are required to use various mathematical functions such as polynomials and exponentials to create a piece-wise function that models the roller coaster track geometry. The entire project is composed of five modules, each lasting three weeks. Each module is associated with a specific calculus topic and is integrated into the design process in a form of a design constraint or performance metric. The module topics include continuity, smoothness, local maxima and minima, inflection points, and area under the curve. Students are expected to refine their models in each module, resulting in the iteration of the previous design to satisfy a new set of requirements. This paper presents the project organization, assessment methods, and student feedback. This work is part of a multi-year course intervention and professional development NSF project to increase the success of underrepresented and women students in engineering. 

ASSURE-US program, started in 2018 through NSF funding, targets first- and second-year engineering and computer science students, especially those underrepresented ones, enrolled at California State University, Fullerton (CSUF) to foster socio-cultural interaction, demonstration-based learning experiences, and curriculum-related research experiences of students. Our activities have affected nearly 400 out of the approximate 4700 students enrolled in engineering and computer science programs at CSUF as of Fall 2020, with many of them as first-year freshman students. In this paper, we present the preliminary findings of the two first-year enrichment programs in ASSURE-US: the student teacher interaction council (STIC) and student summer research, and lessons learned from two years’ implementation of the project in order to improve the project implementations for future years. 

The Introduction to engineering (EGGN-100) is a project-based course offered every fall semester to first-year students with undecided engineering majors at California State University, Fullerton (CSUF). The primary objective of this course is to provide project-based learning (PBL) and introduce these students to major projects in Civil, Mechanical, Electrical, and Computer Engineering projects so that they can make an informed decision about their major. The PBL is an active learning method that aims to engage students in acquiring knowledge and skills through real-world experiences and well-planned project activities in engineering disciplines. The course comprises four team-based unique projects related to Civil, Mechanical, Electrical, and Computer Engineering. The project involves using a variety of engineering tools like AutoCAD, Multisim, and Arduino platforms. For the first time, due to the COVID-19 pandemic, the hands-on project-based EGGN-100 course was offered virtually. In this research, we document the learning experiences of students who attended EGGN-100 in a traditional face-to-face mode of instruction and students who participated in the same course in a virtual instruction mode. Surveys conducted during seemingly different modes of instruction show varying levels of satisfaction among students. Of the students who attended the course in traditional and instructional instruction mode, 69% and 90% responded that discipline-specific projects enabled them to make an informed decision, and PBL helped them choose their preferred major. Even the percentage of students who believed the PBL helped them make an informed decision about their major, they like to do more hands-on projects and prefer to attend the classes on campus. Students rated higher satisfaction in virtual instructional mode primarily due to the availability of video lectures, self-paced learning, and readily accessible project simulations. Learning by doing would have bought out the challenges and minor nuances of designing and executing an engineering project. Learning by watching is surficial and not necessarily exposes students to minor details that are critical. As such, the significance of this study is that maybe, after all, not all courses can be taught in a virtual environment, and some courses may be strictly taught in a traditional, hands-on instruction mode. We also study the socio-psychological impact of traditional and virtual learning experiences and report the remedies to cope with stress and loneliness in the online learning environment.