Artificial Intelligence in form of Machine Learning classifiers is increasingly applied for travel choice modeling issues and therefore constitutes a promising, competitive alternative towards conventional discrete choice models like the Logit approach. In comparison to traditional theory-based models, data-driven Machine Learning generally shows powerful predictive performance, but often lacks in model interpretability, i.e., the provision of comprehensible explanations of individual decision behavior. Consequently, the question about which approach is superior remains unanswered. Thus, this paper performs an in-depth comparison between benchmark Logit models and Artificial Neural Networks and Decision Trees representing two popular algorithms of Artificial Intelligence. The primary focus of the analysis is on the models’ prediction performance and its ability to provide reasonable economic behavioral information such as the value of travel time and demand elasticities. For this purpose, I use crossvalidation and extract behavioral indicators numerically from Machine Learning models by means of post-hoc sensitivity analysis. All models are specified and estimated on synthetic and empirical data. As the results show, Neural Networks provide plausible aggregate value of time and elasticity measures, even though their values are in different regions as those of the Logit models. The simple Classification Tree algorithm, however, appears unsuitable for the applied computation procedure of these indicators, although it provides reasonable interpretable decision rules for travel choice behavior. Consistent with the literature, both Machine Learning methods achieve strong overall predictive performance and therefore outperform the Logit models in this regard. Finally, there is no clear indication of which approach is superior. Rather, there seems to be a methodological tradeoff between Artificial Intelligence and discrete choice models depending on the underlying modeling objective.

No description available.

This empirical exploratory study quantitatively analyzed content similarity indices (potential plagiarism) from a corpus consisting of 360 dissertations and 360 published articles. The population was defined using the filtering search criteria human resource development, training and development, organizational development, career development, or HRD. This study described in detail the process of collecting content similarity analysis (CSA) metadata using Turnitin software (www.turnitin.com). This researcher conducted robust descriptive statistics, a Wilcoxon signed-rank statistic between the similarity indices before and after false positives were excluded, and a multinomial logistic regression analysis to predict levels of plagiarism for the dissertations and the published articles. The corpus of dissertations had an adjusted rate of document similarity (potential plagiarism) of M = 9%, (SD = 6%) with 88.1% of the dissertations in the low level of plagiarism, 9.7% in the high and 2.2% in the excessive group. The corpus of published articles had an adjusted rate of document similarity (potential plagiarism) of M = 11%, (SD = 10%) with 79.2% of the published articles in the low level of plagiarism, 12.8% in the high and 8.1% in the excessive group. Most of the difference between the dissertations and published articles were attributed to plagiarism-of-self issues which were absent in the dissertations. Statistics were also conducted which returned a statistically significant justification for employing the investigative process of removing false positives, thereby adjusting the Turnitin results. This study also found two independent variables (reference and word counts) that predicted dissertation membership in the high (.15-.24) and excessive level (.25-1.00) of plagiarism and published article membership in the excessive level (.25-1.00) of plagiarism. I used multinomial logistic regression to establish the optimal prediction model. The multinomial logistic regression results for the dissertations returned a Nagelkerke pseudo R2 of .169 and for the published articles a Nagelkerke pseudo R2 .095.

The purpose of this study is to demonstrate how to measure skill importance for two sports: soccer and volleyball. A division I women's soccer team filmed each home game during a competitive season. Every defensive, dribbling, first touch, and passing skill was rated and recorded for each team. It was noted whether each sequence of plays led to a successful shot. A hierarchical Bayesian logistic regression model is implemented to determine how the performance of the skill affects the probability of a successful shot. A division I women's volleyball team rated each skill (serve, pass, set, etc.) and recorded rally outcomes during home games in a competitive season. The skills were only rated when the ball was on the home team's side of the net. Events followed one of these three patterns: serve-outcome, pass-set-attack-outcome, or dig-set-attack-outcome. We analyze the volleyball data using two different techniques, Markov chains and Bayesian logistic regression. These sequences of events are assumed to be first-order Markov chains. This means the quality of the current skill only depends on the quality of the previous skill. The count matrix is assumed to follow a multinomial distribution, so a Dirichlet prior is used to estimate each row of the count matrix. Bayesian simulation is used to produce the unconditional posterior probability (e.g., a perfect serve results in a point). The volleyball logistic regression model uses a Bayesian approach to determine how the performance of the skill affects the probability of a successful outcome. The posterior distributions produced from each of the models are used to calculate importance scores. The soccer data importance scores revealed that passing, first touch, and dribbling skills are the most important to the primary team. The Markov chain model for the volleyball data indicates setting 3–5 feet off the net increases the probability of a successful outcome. The logistic regression model for the volleyball data reveals that serves have a high importance score because of their steep slope. Importance scores can be used to assist coaches in allocating practice time, developing new strategies, and analyzing each player's skill performance.

This paper explores the use of Naive Bayes as well a Linear Support Vector Machines in order to classify a text based on the level of medical emergency. The primary source of testing will be an online veterinarian service’s customer data. The aspects explored are whether a single text gives enough information for a medical decision to be made and if there are alternative data gathering processes that would be preferred. Past research has proven that text classifiers based on Naive Bayes and SVMs can often give good results. We show how to optimize the results so that important decisions can be made with these classifications as a basis. Optimal data gathering procedures will be a part of this optimization process. The business applications of such a venture will also be discussed since implementing such a system in an online medical service will possibly affect customer flow, goodwill, cost/revenue, and online competitiveness. / Denna studie utforskar användandet av Naive Bayes samt Linear Support Vector Machines för att klassificera en text på en medicinsk skala. Den huvudsakliga datamängden som kommer att användas för att göra detta är kundinformation från en online veterinär. Aspekter som utforskas är om en enda text kan innehålla tillräckligt med information för att göra ett medicinskt beslut och om det finns alternativa metoder för att samla in mer anpassade datamängder i framtiden. Tidigare studier har bevisat att både Naive Bayes och SVMs ofta kan nå väldigt bra resultat. Vi visar hur man kan optimera resultat för att främja framtida studier. Optimala metoder för att samla in datamängder diskuteras som en del av optimeringsprocessen. Slutligen utforskas även de affärsmässiga aspekterna utigenom implementationen av ett datalogiskt system och hur detta kommer påverka kundflödet, goodwill, intäkter/kostnader och konkurrenskraft.

This thesis investigates imbalanced Swedish text financial datasets, specifically receipt classification using machine learning models. The study explores the effectiveness of under-sampling and over-sampling methods for Naive Bayes algorithms, collaborating with Fortnox for a controlled experiment. Evaluation metrics compare balancing methods regarding the accuracy, Matthews's correlation coefficient (MCC) , F1 score, precision, and recall. Findings contribute to Swedish text classification, providing insights into balancing methods. The thesis report examines balancing methods and parameter tuning on machine learning models for imbalanced datasets. Multinomial Naive Bayes (MultiNB) algorithms in Natural language processing (NLP) are studied, with potential application in image classification for assessing industrial thin component deformation. Experiments show balancing methods significantly affect MCC and recall, with a recall-MCC-accuracy tradeoff. Smaller alpha values generally improve accuracy.  Synthetic Minority Oversampling Technique  (SMOTE) and Tomek's algorithm for removing links developed in 1976 by Ivan Tomek. First Tomek, then SMOTE (TomekSMOTE)  yield promising accuracy improvements. Due to time constraints, Over-sampling using SMOTE and cleaning using Tomek links. First SMOTE, then Tomek (SMOTETomek) training is incomplete. This thesis report finds the best MCC is achieved when $\alpha$ is 0.01 on imbalanced datasets.

This thesis covers two separate studies. The first study, chapter 2, was conducted to evaluate whether there are additional economic returns from producing strawberries in the high tunnel compared to the open-field in Southeast Virginia. We develop and compare budgets for eight strawberry cultivars grown in the two environments and sold under three marketing strategies (pre-pick wholesale, pre-pick retail, and U-pick). Almost all cultivars in the high tunnel generated negative net revenues regardless of the marketing strategy. In contrast, net revenues from open-field cultivars were always positive. In the second study, chapter 3, we used a fractional multinomial logit model to estimate the effect of crop revenues, input costs, and fuel ethanol production on the joint acreages planted to eight U.S major crops (barley, corn, cotton, peanuts, rice, sorghum, soybeans, and wheat). We found a positive and statistically significant marginal effect of the expected peanuts' revenue on its acreage share. The expected corn revenue had a negative average marginal effect on soybean acreage share, and the effect of expected wheat revenue was positive on cotton acreage share and negative on rice acreage share. / Master of Science / This thesis covers two separate research studies. The first study, chapter 2}, was conducted to evaluate whether growing strawberries in a simple, low-cost, and passive heat structure known as a "high tunnel" would yield more profit (the difference between total revenues and total costs) compared to growing them outside in an open-field in Southeast Virginia. We estimate and compare differences between total revenues and costs for eight strawberry cultivars grown in the two environments and sold under three marketing strategies. The first two marketing strategies involve growers harvesting strawberries themselves. They can then either retail them (farm stands, farmers' markets, or in a similar setting: pre-pick retail) or sell them in bulk to be retailed by others (pre-pick wholesale). A third marketing strategy involves consumers visiting a farm and picking their own strawberries (U-pick). Almost all cultivars grown in the high tunnel structure resulted in a loss (negative difference between total revenues and costs) regardless of the marketing strategy. In contrast, cultivars produced in the open-field always generated a profit (positive total revenues and costs difference). In the second study, chapter 3, we estimated the effect of crop revenues, input costs, and fuel ethanol production on acreages planted to eight U.S major crops (barley, corn, cotton, peanuts, rice, sorghum, soybeans, and wheat), and we considered the fact that acreages allocated to one crop affect other crops' acreages. We found that increasing the expected revenue of peanuts leads to an increase in its acreage share. Increasing the expected revenue of corn leads to a decrease in soybeans' acreage share. Finally, increasing the expected revenue of wheat leads to an increase in the cotton acreage share and a decrease in the rice acreage share.

No description available.

No description available.

No description available.