BEGIN:VCALENDAR VERSION:2.0 PRODID:-//TUC//Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Athens TZNAME:EEST DTSTART:19700329T030000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0300 TZNAME:EET DTSTART:19701025T040000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 END:STANDARD END:VTIMEZONE BEGIN:VEVENT CREATED:20220725T115753Z LAST-MODIFIED:20220725T115753Z DTSTAMP:20260614T160010Z UID:1781442010@tuc.gr SUMMARY:παρουσίαση μεταπτυχιακής εργασίας κ. Αντωνίας Τρικουνάκη, Σχολή ΜΠΔ LOCATION: DESCRIPTION:https://www.tuc.gr/el/to-polytechnei o/ilektronikes-ypiresies/imerologio/ imerologio-ekdiloseon-1?tx_tucevents 2_tuceventsdisplay%5Baction%5D=show& tx_tucevents2_tuceventsdisplay%5Bcon troller%5D=Event&tx_tucevents2_tucev entsdisplay%5Bevent%5D=5725&cHash=6a 9d5c78f45b5dda35ac23a6919af2ee\nΠΟΛΥ ΤΕΧΝΕΙΟ ΚΡΗΤΗΣ\n ΣΧΟΛΗ ΜΗΧΑΝΙΚΩΝ ΠΑΡ ΑΓΩΓΗΣ ΚΑΙ ΔΙΟΙΚΗΣΗΣ\n  \n Name & ; Surname: ……Antonia Trikounaki…………… ………………………… \n Reg. Number: ……2020015 003…………………………………………… \n  \n Subject  \n Title: …Business Decision Analysi s Based on Data Analytics…………………………… ……………… \n  \n Examination Committee:  \n Supervisor: …Matsatsinis Nikolao s……………………………………… \n First Member: …… …Batsakis Sotirios……………………………… \n Se cond Member: …Tsafarakis Stelios………… ……….………….…… \n  \n Abstract: \n Desp ite the continuous and exponential t echnological evolution, a common phe nomenon observed in the service and retail industry is the lack of patte rn recognition in a dataset and thus the inability to create predictions on business issues. This, makes the m even more susceptible to uncertain ty and risk, as they are not able to focus on the key variables that inf luence their companies' attributes.   \n This thesis, highlights three di fferent case studies of companies op erating in the service and retail in dustry. Specifically, the paper focu ses on the case of a hotel company b ased in Chania of Crete, a multinati onal insurance company and a big Gre ek Super Market chain, that seek to use data analysis along with data sc ience to extract the necessary infor mation and make the predictions need ed in order to take effective decisi ons and improve their business perfo rmance.  \n The aforementioned, can be achieved by using the methods of categorization, clustering and assoc iation rule mining through the usage of machine learning software, WEKA. Through algorithms' implementation, it is possible to make predictions, check their accuracy, create patter ns of interrelated sales/purchases a nd group features, based on the data provided by the companies.  \n In e ach of these three cases, the datase t is examined, and through WEKA'S as sistance, the data is analyzed in or der to obtain results, capable of as sisting or improving decision-making , increasing competitiveness and pos sibly increasing the sales of the fi rms in question. \n The first chapte r presents the concept of data minin g, the purpose it serves and the way s through which it helps in business problem solving. Then the data mini ng software- WEKA is presented, whic h is used in each of the cases, to a nalyze the data given and to provide meaningful patterns, rules and resu lts for the issues addressed. The pr esentation, analysis and explanation of the different regression and cla ssification algorithms follows, whic h will be used in the use cases of t he following chapters and the differ ent clusterers that will be applied through WEKA’s software. Additionall y, the concept of association rule m ining is presented and explained, as well as the various metrics that wi ll be used to analyze and interpret WEKA’s  results. \n The second chapt er presents the Creta Palm Hotel’s c ase. For this case, a certain amount of data, concerning the hotel’s boo kings from the different travel agen cies as well as the different bookin g sources was collected, for the yea rs 2019 and 2020. This data is about to be analyzed through classificati on algorithms' implementations and c lustering method developments, with the assistance of the machine learni ng software WEKA. This aims in gener ating predictions for the total book ings of the different travel agencie s and the different booking pages, i n checking the accuracy of the total bookings’ predictions as well as in grouping the different co-operative booking sources' characteristics ba sed on the years of 2019 and 2020. T otal bookings’ predictions concern a ll those travel agencies and booking sources that have the same, or simi lar characteristics to the agencies/ sources given for analysis, that is the training data. The agencies/sour ces whose data have the same or simi lar characteristics to the training data, are expected to behave in the same way and have similar number of sales. \n The third chapter is about the multinational insurance company NN. In this case, the company creat ed a questionnaire for its customers and collected their responses, in o rder to examine their intentions and preferences concerning the insuranc e products she promotes. These respo nses, are being processed and then a nalyzed, in order to predict the cus tomers’ interest for insurance estim ating, to test the predictions’ accu racy and to cluster the customers’ c haracteristics, based on the data pr ovided by the company. The aforement ioned are accomplished, through clas sification algorithms’ implementatio n and clustering methods’ developmen t, with the assistance of WEKA machi ne learning software. WEKA’s predict ions for the customers’ interest in retirement estimation, concern custo mers who display the same or similar characteristics as those of the cus tomers answering the questionnaire. Therefore, customers with the same o r similar characteristics as the tra ining data are expected to behave in the same way and have a similar res ponse. \n The forth chapter presents the case of a large Super Market in Greece. For this use case, a databa se with transactional and demographi c data was collected from the Superm arket for a period of eight months d uring 2021. This database included t he customers’ gender, age, card code and all of their purchases with its dates, the shop and area from which the customers made each purchase, t he products each customer chose alon g with their product category and th e amount of money that they spent on each product. The collection and an alysis of these data, gives us the o pportunity to find useful informatio n about the customers, through assoc iation rule mining and clustering. W eka Machine Learning Software, trans forms the dataset into meaningful pa tterns with the assistance of integr ated algorithms, aiming to find the products that appear an association with each other and are usually purc hased together (association rule min ing) as well as to group the custome rs depending on their purchase frequ ency of the various product categori es. Association rule mining- in othe r words- market basket analysis, dis covers the correlations between the different items in customers’ shoppi ng cart and clustering segregates gr oups with similar traits. These meth ods help the company to have a bette r understanding of the customers’ pr ofile and thus, create value for the m. This leads to a better customer e xperience and creates a stronger sen timent or loyalty towards the compan y. The methods of association rule m ining and clustering helps the compa ny to better predict the results of a new oncoming dataset that has simi lar characteristics with our already existing dataset and make the neces sary marketing campaigns depending o n the customers’ gender, age and are a of shopping. \n  \n Examination Da te: \n Day/Month/Year: ………27/07/2022 ………… \n Time: ………13:00……………………………… \ n  \n Examination Venue: \n Auditori um/ Lecture Room:   https://tuc-gr.z oom.us/j/97509504080?pwd=dng3UWF5Q0N xUzQ3Rm1mbkRwdDFnQT09   \n Building: …………………………..……………………………… \n STATUS:CONFIRMED ORGANIZER;RSVP=FALSE;CN=TUC;CUTYPE=TUC:mailto:webmaster@tuc.gr DTSTART:20220727T130000 DTEND:20220727T140000 TRANSP:OPAQUE CLASS:DEFAULT END:VEVENT END:VCALENDAR