Бакалаврська програма "ІТ та бізнес-аналітика"
Permanent URI for this communityhttps://hdl.handle.net/20.500.14570/3861
Browse
Search Results
Item Optimization of the product concept for the videogame market by applying econometric modelling(2022) Zahartovskyi, MarkoThe video game industry is a mix of technologies and art. This is a rapidly evolving market which captures the look of many dreamers. They are not marketing specialists or experts in statistics. They have only their vision to guide them. Because of this, it is tough to find the right product concept for this market and entering this industry brings many risks. This thesis is created to help independent game developers find an alternative to their "gut assumption" in a data-driven approach using econometric modelling tools.Item Detecting conditions that cause unstable sensor road test readings: using Quality Control Charts(2022) Vorobchuk, AlinaRoad infrastructure plays a significant role in a country’s economic development. To maintain this vital infrastructure, road maintenance and preservation are extremely important. Weigh-in-motion (WIM) technology is a practical and economic solution to mitigate some of the consequences of road deterioration. While WIM systems have a number of advantages; their main drawback is the measurement accuracy. The quality of the sensor readings is highly dependent on different environmental factors, which may cause anomalous values in data. My thesis focuses on detecting abnormal sensor values and identifying the reasons that caused such sensor readings. This paper examines the effectiveness of applying the Quality Control Charts for detecting abnormal sensor values in WIM tests. The project aims to provide recommendations that help understand the features and limitations of road sensors in various environmental conditions. Furthermore, this work can serve as a basis for further studies in the field of road construction.Item Churn Prediction Model and Segmentation in Insurance Industry(2022) Tytarenko, ViktorIncreasing competition in US Insurance Industry pushes companies to raise marketing costs and decrease prices to get new customers. As a result, customer acquisition costs sky rocketed, and the only way for companies to be profitable is to keep stable retention and reduce churn. Without data-driven decisions, companies struggle to reduce churn and eventually lose their momentum in a hardly competitive industry. The main goal of this paper is to analyze customer data, describe churn behavior, and develop action able recommendations to decrease customer churn. We developed a churn prediction model and segmented churnedcustomers. Segmentation combined with model results were used to develop segment-specific recommendations for the business. The business implication of this research is a churn reduction strategy designed specifically for each customer segment.Item Developing an ensemble approach for predicting customer churn in telecommunication industry(2022) Todoshchuk, NazarCustomer satisfaction and retention are key goals and, at the same time challenges, for most of the modern companies which try to keep up with the times. To identify and retain the customers who are most likely to ‘break ties’ with the company, the latter spend much financial and technological resources. Those include advanced machine learning algorithms for customer churn prediction. This thesis explores a number of different common ML algorithms, including logistic regression, support vector machines, decision tree, random forest and XGBoost, which predict customer churn in wireless telecommunication industry. To mitigate the risks of non-accurate predictions, an ensemble algorithm is developed based on the weighted voting approach. In this thesis the performance of ensemble algorithm will be compared to those of all above mentioned to rank them by prediction accuracy and choose the best-performing one.Item Developing Advanced Driver-Assistance Systems using computer vision and machine learning for driver safety use cases(2022) Teliuk, ArtemThe automotive industry is increasingly using evolving technologies to increase driving comfort and safety. In addition to direct assistance systems for vehicle control (such as ABS, ESC, or ASR), there are also informational systems that warn the driver of the danger or provide the necessary information. Such systems include collision warnings, lane departure warnings, allocating pedestrians, and determining the distance to the car in front. These systems are considered Advanced Driver Assistance Systems and can be found as part of a high-end car kit or as an expensive option. Most of these systems depend on various devices and sensors, such as radars, LIDARS, and GPS modules. With the development of artificial intelligence and computer vision technologies, we have the opportunity to replace these components by creating software and obtaining only video data. This will significantly reduce the cost of production of such systems, make them more accessible for installation in cars that were not initially designed to include those functions, and will be able to supplement existing systems to increase accuracy and thus improve driving safety. This work aims to create a comprehensive system of driver assistance using only footage from the video of the road situation in front of the car and technology of artificial intelligence and computer vision.Item Diagnosis of neurological and psychiatric diseases based on whole-brain functional connectivity using Machine Learning techniques(2022) Tatosh, SofiiaThe global problem this thesis aims to target is the inability of psychotherapists and psychiatrists always correctly to identify a presence of a mental illness. To give a constructive medical conclusion on a patient’s state, usually, it is not enough to only rely on symptoms concluded from a therapeutic session. Moreover, the diagnosis of that kind could be biased from both a therapist and a patient’s side. The former depends on the doctor’s knowledge and experience, and the latter is based on an ability to communicate the mental state. Notably, the more researchers investigate the cause of psychiatric diseases, the more they make sure that mental illnesses are developed due to specific changes in one’s brain. It could be the brain’s structure, functionality, or damage, leading to changes in a person’s behavior, thought process, interaction with other people, and sometimes difficulties in functioning as a healthy human being. It is believed that severe mental illnesses and neurological and developmental diseases result from abnormal connectivity in a brain network. That is why whole-brain functional connectivity is a significant source of information in this study. In simple words, it represents if and how the brain regions communicate with each other. This study presents generalized, usable, and reliable classification models to identify a specific neurological or psychiatric disease, Autism Spectrum Disorder and Schizophrenia, with 92.4% and 93.8% of accuracy respectfully, for further clinical application of the developed tool.Item Automatic summary generation and topic modeling of Ukrainian news articles(2022) Tananaiska, AnastasiiaWith the growth of the amount of textual information produced by news media daily, keeping up with the most recent events happening in the world can lead to a really overwhelming experience. Especially when living through those events or possibly witnessing those in real life. The focus of this work will be, in fact, on the development of the solution to the problem of information overload, addressed by generating summaries and classifying topics of the news articles.Item Data-driven supply planning for a humanitarian aid center during war(2022) Sorokotyaha, SolomiyaConsequences of natural disasters and military conflicts are becoming more devastating with the increase of population. Supply planning is widely studied and applied in commercial sectors, while not being fully benefited from by the humanitarian aid organizations. Volunteering movements fill gaps in which more formal, structured organizations are not able to respond. This project examined the operations of grassroots organizations during the russian invasion of Ukraine in 2022. A stakeholder analysis and a detailed research of fulfillment of the request process and inventory management of the grassroot volunteering center was conducted, based on centers request and supply real-time data, personal interviews of volunteers, life process observations. As a result, this project offers recommendations how to start using data for decisions makers in volunteering centers, including supply planning, providing an example for other similar centers. The project offers a good starting point for future research.Item Prognostication model and pricing strategy optimization for restaurant businesses(2022) Shuptar, SolomiyaThe aim of this thesis is to study price elasticity for this type of consumer product such as confectionery, in order to find out the relationship between price and demand. Since very few companies change the price in both directions for research, we will need to simulate how the demand would change if the price will be moved by an arbitrary percentage rate. The result of this work will be a revealing of the correct elasticity between demand and price for every product, which will allow to improve current pricing strategy and optimize the model of sales with relation to retail prices.Item Developing recommendations to increase adoption rate of eronomic scalpels on the US market of surgical instruments(2022) Petsiukh, SofiiaThe history of scalpel usage in medicine goes back to the ancient times. And through- out all that time the scalpel design has not gone through a major improvement pro- cess compared to other medical devices. If we look at the pictures of knives that early Egyptians used, they will not differ significantly from what the doctors use today during surgery. Dr.Raymond Dunn, a practicing plastic surgeon at UMass Medical Hospital, saw the room for improvement and created a design of an er- gonomic scalpel handle to improve doctors’ experience. However, the market of surgical scalpels already has a number of approved and tested by time products, so entering it will be a challenge. In this bachelor thesis, I will look at important aspects of the scalpels market in the US and develop recommendations to increase the adoption rate of ergonomic scalpels designed by Dr. Dunn. To achieve this I use Business Analysis techniques and apply the Axiomatic Design methodology to design the steps for a successful market entry. The results of my work state that in order to increase adoption rate of scalpels it is necessary to conduct further test- ing with the current prototype, collect enough data to understand the interest of the market. If needed, the design should be augmented to better fit custome needs.It is also important to find product champions, who would advocate for the advantages of the product in fron tof VACs.