https://ir.unisa.ac.za/handle/10500/21673 2026-05-05T16:16:08Z https://ir.unisa.ac.za/handle/10500/32281 Implementation of electronic signatures to increase productivity and mitigate risk within the conveyancing process in South Africa Abrahams, Luke This study’s aims are to investigate how electronic signatures can mitigate risks and increase productivity within South Africa’s conveyancing process. The transfer of land ownership in South Africa is often complex, inefficient and time-consuming, compounded by manual signature authentication, limited digitisation and concerns around fraud and security. The study explores whether electronic signature technology can enhance efficiency and protect against signature-related fraud, such as unauthorised document alterations or identity theft. Using a qualitative research method, data were collected through twelve online semi-structured interviews focusing on three major conveyancing organisations in South Africa and document analysis of six documents to triangulate the findings. The three organisations are recognised for their legal authority in facilitating the compilation and signing of property-related documents. The audio-recorded interviews and document data were analysed using content analysis whereby themes and subthemes were identified after using open coding. Ethical principles were followed, and participant informed consent was obtained, with ethical clearance and permission obtained before data collection commenced. This study was limited to personal interviews within the conveyancing industry, relying on self-reported data. Time constraints and the use of closed-ended questions further restricted the depth of analysis. This study was further limited to the implementation of electronic signatures for productivity, excluding the full land transfer process and its bottlenecks. This research contributes to the literature and provides new insights into how electronic signatures, if implemented, could improve productivity and efficiency within the land transfer processes. This research highlights both the challenges and opportunities of adopting electronic signatures, including the legal and regulatory framework governing their use, as well as the potential for conveyancers to drive digital transformation in the industry. The findings indicate that several barriers impact the implementation of electronic signatures in the conveyancing industry, such as legal restrictions, high technology costs, and inconsistencies in signature verification methods. However, the study concludes that adopting electronic signatures can reduce risks and enhance productivity by streamlining the signing process, improving security through audit trails and encryption, and reducing manual document 3 handling. Electronic signatures offer distinct advantages over handwritten signatures, facilitating operational efficiency and strategic value for organisations. Robust security measures are essential to ensure that these benefits are fully realised, making electronic signature technology a crucial component of digital transformation in conveyancing. The recommendations of the findings indicate that there is a need for investment in training and upskilling staff on issues related to information security and specifically cybercrime. Additionally, conveyances should seek to standardise manual signature and document vetting while integrating elements of the Parkerian Hexad model namely confidentiality, integrity, availability, authenticity and utility. These principles enhance fraud prevention and ensure signed documents remain secure and unaltered. In addition, legal policymakers should consider updating legislation to include provisions for electronic signatures within the land transfer process. Furthermore, the deeds office remains a central role player in land transaction processes and should invest in the necessary infrastructure and workforce training to implement electronic signatures, cloud storage and the verification processes needed by conveyancers to improve security, mitigate risks and streamline operations.; Iinjongo zolu phandolwazi kukuphanda indlela utyikityo lwe-elektroniki olunokuthi lunciphise ngayo imingcipheko kunye nokwandisa imveliso kwinkqubo yobhalisozitayitile yoMzantsi Afrika. Ukugqithiselwa kobunini bomhlaba eMzantsi Afrika kudla ngokubanzima, kungasebenzi kwaye kutye ixesha, kusokoliswa luqinisekiso lotyikityo olwenziwa ngesandla, ukunqongophala koguqulelolwazi kwidijithali kunye neenkxalabo zobuqhophololo nokhuseleko. Olu phandolwazi luphonononga ukuba ingaba ubuchwepheshe botyikityo lwe-elektroniki bungaphucula ukusebenza kakuhle kwaye bukhusele kubuqhophololo obunxulumene nokutyikitya, obufana nokutshintshwa kwamaxwebhu okungagunyaziswanga okanye ubusela bezazisi. Idatha iqokelelwe ngokusebenzisa isikhokelo sophandontyilazwi ngodliwanondlebe lwangentanethi olucwangciswe mayane nabathathinxaxheba abalishumi elinambini, lugxile kumaqumrhu amathathu amakhulu obhalisozitayitile eMzantsi Afrika kunye nohlalutyo lwamaxwebhu amathandathu ukuqinisekisa ubunyani nokuthembeka kweziphumo. La maqumrhu mathathu aqinisekisiwe ngegunya lawo elisemthethweni ekuququzeleleni ukuqulunqwa nokutyikitywa kwamaxwebhu anxulumene nepropati. Udliwanondlebe olurekhodiweyo kunye neenkcukacha zamaxwebhu zihlalutywe kusetyenziswa uhlalutyo lomxholo apho kuye kwachongwa imixholo nemixholwana emva kokusetyenziswa kohlalutyo lokuhlelwa kwedatha ngokwemixholo. Ilandelwe imigaqo yokuziphatha kuphandolwazi, kwaye nemvume yokuthatha inxaxheba kwabathathinxaxheba kuphandolwazi iye yafunyanwa, nemvume nokuvunyelwa komphandilwazi ukuba aqhube uphandolwazi ethe yafunyanwa ngaphambi kokuba kuqaliswe ukuqokelela idatha. Olu phandolwazi belugxile kudliwanondlebe nabantu ngaphakathi kwicandelo lobhalisozitayitile, ngokuxhomekeke kwidatha ezichazayo. Ubunzulu bohlalutyo lwedatha buye bathintelwa ngakumbi yimiqobo yexesha nokusetyenziswa kwemibuzo evalelekileyo. Luphinde lwanyinwa ekuphunyezweni kotyikityo lwe-elektroniki ukwenzela imveliso, ngaphandle kwenkqubo epheleleyo yokudluliselwa komhlaba kunye nemiqobo yayo. Olu phandolwazi lunegalelo kuncwadi kwaye lubonelela ngeengcamango ezintsha malunga nokuba, ukuba utyikityo lwe-elektroniki luyafezekiswa, lungaphucula imveliso kunye nokusebenza kakuhle phakathi kwiinkqubo zokudlulisela umhlaba. Lukwabhentsisa imingeni namathuba okwamkela utyikityo lwe-elektroniki, kubandakanywa nesikhokelo somthetho nesolawulo esilawula ukusetyenziswa kolu tyikityo, kwakunye nokubanakho kwababhalisizitayitile ukuzisa inguqu yedijithali kweli candelo. Iziphumo zibonisa ukuba kukho imiqobo emininzi enempembelelo ekuphunyezweni kotyikityo lwe-elektroniki kwicandelo lobhalisozitayitile, efana nezithintelo zomthetho, iindleko eziphezulu zobuchwepheshe, kunye nokungahambelani kwiindlela zokuqinisekisa utyikityo. Nangona kunjalo, olu phandolwazi luqukumbela ukuba ukwamkela utyikityo lwe-elektroniki kunganciphisa imingcipheko kwaye kuphucule imveliso ngokulungelelanisa inkqubo yokutyikitya, ukuphucula ukhuseleko ngeendlela zophicothozincwadi noguqulelo oluntsonkothileyo, kunye nokunciphisa ukuphathwa kwamaxwebhu ngesandla. Utyikityo lwe-elektroniki lubonelela ngoncedo olwahlukileyo kutyikityo olubhalwe ngesandla, luququzelela ukusebenza kakuhle kunye nexabiso lobuchule bokusebenza kumaqumrhu. Abalulekile amanyathelo okhuseleko omeleleyo ukuqinisekisa ukuba le nzuzo ifezekiswa ngokupheleleyo, okwenza ukuba ubuchwepheshe botyikityo lwe-elektroniki bube yinxalenye ebalulekileyo yenguqu yedijithali kubhalisozitayitile. Izindululo zeziphumo zibonisa ukuba kukho imfuneko yotyalomali ekuqeqesheni nasekuphuculeni izakhono zabasebenzi kwimiba enxulumene nokhuseleko lolwazi ingakumbi ulwaphulomthetho ngezobuchwepheshe. Ukongeza, kufuneka icandelo lobhalisozitayitile likhangele ukulungelelanisa utyikityo olwenziwa ngesandla kunye novavanyo lwamaxwebhu ngelixa kuhlanganiswa izinto eziyinxalenye yeParkerian Hexad model ezizezi, ubumfihlo, ingqibelelo, ukufumaneka, ukunyaniseka kunye nokuba luncedo. Le migaqo iphucula uthintelo lobuqhophololo kwaye iqinisekisa ukuba amaxwebhu atyikityiweyo ahlala ekhuselekile kwaye engenakutshintshwa. Ukongeza, kufuneka abaqulunqi bomgaqonkqubo womthetho bacinge ngokuhlaziya umthetho ukuze ubandakanye izibonelelo zotyikityo lwe-elektroniki ngaphakathi kwinkqubo yokudluliselwa komhlaba. Ngaphaya koko, iofisi yeetayitile ihlala idlala indima ebalulekileyo kwiinkqubo zentengiselwano yomhlaba kwaye kufuneka ityale imali kwiziseko ezingundoqo eziyimfuneko kunye noqeqesho lwabasebenzi ukuze kufezekiswe utyikityo lwe-elektroniki, ukugcinwa kwedatha yekhompyutha kunye neenkqubo zokuqinisekisa ezidingwa ngababhalisizitayitile ukuphucula ukhuseleko, ukunciphisa imingcipheko kunye nokulungelelanisa iinkqubo zomsebenzi.; Hierdie studie se doel is om te ondersoek hoe elektroniese handtekeninge risiko’s kan verminder en produktiwiteit kan verhoog in Suid-Afrika se transportbesorgingsproses. Die oordrag van grondbesit in Suid-Afrika is dikwels ingewikkeld, ondoeltreffend en tydrowend, en dit word verder bemoeilik deur geskrewe handtekeningverifikasie, beperkte digitalisering en bekommernisse oor bedrog en sekuriteit. Die studie verken of elektroniese handtekeningtegnologie doeltreffendheid kan verbeter en ’n mens kan beskerm teen handtekening-verwante bedrog, soos ongemagtigde dokumentwysigings of identiteitsdiefstal. ’n Kwalitatiewe navorsingsmetode is gebruik om data in te samel deur middel van 12 aanlyn halfgestruktureerde onderhoude met die fokus op drie groot transportbesorgingsorganisasies in Suid-Afrika, asook dokumentontleding van ses dokumente om die bevindings te trianguleer. Die drie organisasies word erken vir hulle wetlike gesag wat betref die fasilitering van die samestelling en ondertekening van eiendomverwante dokumente. Die oudio-opgeneemde onderhoude en dokumentdata is ontleed deur inhoudsanalise waar temas en subtemas geïdentifiseer is ná die gebruik van ope kodering. Etiese beginsels is gevolg en ingeligte toestemming is by deelnemers verkry. Etiese klaring en toestemming is verkry voordat daar met die insameling van data begin is. Hierdie studie is beperk tot persoonlike onderhoude in die transportbesorgingsbedryf en het berus op selfgerapporteerde data. Tydsbeperkings en die gebruik van geslote vrae het die diepte van die ontleding verder beperk. Hierdie studie is ook beperk tot die implementering van elektroniese handtekeninge vir produktiwiteit, en het nie die volledige grondoordragproses en knelpunte ingesluit nie. Hierdie navorsing dra by tot die literatuur en bied nuwe insigte oor hoe elektroniese handtekeninge, indien dit geïmplementeer word, produktiwiteit en doeltreffendheid in die grondoordragprosesse kan verbeter. Hierdie navorsing beklemtoon sowel die uitdagings as die geleenthede wat betref die aanname van elektroniese handtekeninge, insluitende die wetlike en regulatoriese raamwerk wat die gebruik daarvan beheer, asook die potensiaal vir transportbesorgers om digitale transformasie in die bedryf te dryf. Die bevindings dui aan dat verskeie hindernisse ’n invloed het op die implementering van elektroniese handtekeninge in die transportbesorgingsbedryf, soos wetlike beperkings, hoë 5 tegnologiekoste en strydighede wat handtekeningverifikasie-metodes betref. Die studie het egter beslis dat die aanname van elektroniese handtekeninge risiko’s kan verminder en produktiwiteit kan verbeter deur die ondertekeningsproses te vereenvoudig, sekuriteit te verbeter deur ouditspore en enkripsie, en die hantering van dokumente met die hand te verminder. Elektroniese handtekeninge het duidelike voordele bo handgeskrewe handtekeninge, en fasiliteer operasionele doeltreffendheid en strategiese waarde vir organisasies. Goeie sekuriteitsmaatreëls is noodsaaklik om te verseker dat hierdie voordele ten volle verwesenlik word, en verseker dus dat elektroniese handtekeningtegnologie ’n noodsaaklike komponent is wat digitale transformasie in transportbesorging betref. Die aanbevelings van die bevindings dui aan dat daar ’n behoefte is om personeel op te lei en hulle vaardighede uit te brei wat aangeleenthede betref wat verband hou met inligtingsekuriteit en spesifiek kubermisdaad. Verder moet transportbesorgers daarna streef om handgeskrewe handtekeninge en dokumentkeuring te standaardiseer terwyl hulle elemente van die Parkerianse sespuntmodel (Parkerian Hexad model) – vertroulikheid, integriteit, beskikbaarheid, egtheid en nut – integreer. Hierdie beginsels bevorder die voorkoming van bedrog en verseker dat getekende dokumente veilig en onveranderd bly. Verder moet beleidmakers dit oorweeg om wetgewing by te werk om bepalings in te sluit vir elektroniese handtekeninge in die grondoordragproses. Die aktekantoor moet ook ’n sentrale rolspeler bly in grondoordragprosesse en moet belê in die nodige infrastruktuur en opleiding van die arbeidsmag om elektroniese handtekeninge, wolkberging (cloud storage) en die verifikasieprosesse wat deur transportbesorgers benodig word te implementeer om sekuriteit te verbeter, risiko’s te verminder en bedrywighede te vereenvoudig. 2024-10-01T00:00:00Z https://ir.unisa.ac.za/handle/10500/31873 Developing a framework for the adaption of lean manufacturing principles for state-owned entities in South Africa Thango, Unathi Imagine a South Africa where state-owned entities (SOEs) not only drive economic growth but also deliver impeccable services to citizens, all while operating efficiently and sustainably. Unfortunately, this vision is currently marred by governance issues, mismanagement, and waste within SOEs. Although much has been discovered about lean manufacturing as a methodology that promises to reduce waste and improve efficiency, the examination of various lean manufacturing frameworks revealed certain gaps. The first gap is that none of the frameworks proposed in the literature review offers a tailored fit for the adaption of lean principles within the public sector environment. The second gap is a noticeable inclination to a top-down approach among the reviewed lean manufacturing frameworks. This propensity, although appropriate in certain contexts, may face constraints when implemented in the case of SOEs in South Africa. Drawing upon insights from contingency theory, this study revealed both the potential advantages and hurdles associated with the application of lean manufacturing principles to SOEs in South Africa. The researcher examined the systematic interplay of lean principles within the SOE context through the lens of viable systems theory (VST). The study therefore laid out an argument for developing an effective lean framework that is tailored for the reinterpretation of lean principles and concepts according to the unique nature of the public sector. The Schedule 2 SOEs in South Africa constituted the target population of the study. The qualitative sample comprised 10 participants from each entity. The systematic interaction of the lean principles with the context of the SOEs was explored from the perspective of VST and contingency theory, laying out an argument for a framework that demonstrates that it is possible to adapt lean principles to SOEs for value creation and the reduction of waste. A qualitative methodology in the interpretivist paradigm was employed to investigate three Schedule 2 SOEs. Thirty participants were purposively selected for semi-structured online interviews. It was found that value creation by an organisation's leadership requires the participation of both internal and external stakeholders. It is essential to have the backing of important external stakeholders, including government, partners, users, interest groups, and donors, to create value effectively. Through stakeholder consultation, the leadership of an organisation can gain insights into the needs and expectations of the organisation's customers, enabling it to tailor its services and initiatives to meet these needs effectively. The implications of ignoring the reinterpretation of these themes may lead to the use of inappropriate or unhelpful measurements involving the numerical quantification of quality through targets and create impossible expectations in citizens, leading to frustration and dissatisfaction. The implementation of lean manufacturing principles should begin with understanding and determining the context within which SOEs operate. The context of an organisation includes factors such as the organisation's structure, culture, strategic goals, and stakeholders, together with legislative and other requirements, which is important when considering the implementation of lean manufacturing principles.; Stel jou ’n Suid-Afrika voor waar staatsentiteite nie net ekonomiese groei aandryf nie maar ook onberispelike dienste aan burgers lewer, terwyl dit doeltreffend en volhoubaar funksioneer. Ongelukkig word hierdie visie tans geskend deur regeringskwessies, wanbestuur en vermorsing in staatsentiteite. Hoewel daar baie ontdek is oor skraal vervaardiging as ’n metodologie met die belofte om vermorsing te verminder en doeltreffendheid te verbeter, het die ondersoek van verskeie skraal ververvaardigingsraamwerke sekere gapings getoon. Die eerste gaping is dat nie een van die raamwerke wat in die literatuuroorsig voorgestel is ’n aangemete passing bied vir die aanname van skraal beginsels in die openbaresektoromgewing nie. Die tweede gaping is ’n merkbare geneigdheid vir ’n afwaartse benadering onder die hersiende skraal vervaardigingsraamwerke. Hierdie geneigdheid, hoewel toepaslik in sekere kontekste, kan beperkings hê wanneer dit in die geval van staatsentiteite in Suid-Afrika geïmplementeer word. Met insigte van die gebeurlikheidsteorie het hierdie studie sowel die potensiële voordele as die struikelblokke getoon wat geassosieer word met die toepassing van skraal vervaardigingsbeginsels op staatsentiteite in Suid-Afrika. Die navorser het die stelselmatige interaksie van skraal beginsels in die staatsentiteitskonteks ondersoek deur die lens van ’n uitvoerbare stelselteorie. Die studie het dus ’n argument uiteengelê vir die ontwikkeling van ’n doeltreffende skraal raamwerk wat gemaak is vir die hervertolking van skraal beginsels en konsepte volgens die unieke aard van die openbare sektor. Die Skedule 2-staatsentiteite in Suid-Afrika het die teikenpopulasie van die studie uitgemaak. Die kwalitatiewe steekproef het bestaan uit tien deelnemers van elke entiteit. Die stelselmatige interaksie van die skraal beginsels met die konteks van die staatsentiteite is verken uit die perspektief van die uitvoerbare stelselteorie en gebeurlikheidsteorie, en lê ’n argument vir ’n raamwerk uiteen wat demonstreer dat dit moontlik is om skraal beginsels aan te neem vir staatsentiteite vir waardeskepping en die vermindering van vermorsing. ’n Kwalitatiewe metodologie in die interpretivistiese paradigma is aangewend om drie Skedule 2-staatsentiteite te ondersoek. Dertig deelnemers is doelbewus gekies vir halfgestruktureerde aanlyn onderhoude. Daar is gevind dat waardeskepping deur ’n organisasie se leierskap die deelname van beide interne as eksterne belanghebbers benodig. Dit is noodsaaklik om die ondersteuning van belangrike eksterne belanghebbers te hê, insluitende die regering, vennote, gebruikers, belangegroepe en skenkers, om doeltreffend waarde te skep. Die leierskap van ’n organisasie kan deur belanghebberkonsultasie insigte verkry in die behoeftes en verwagtings van die organisasie se kliënte, en die organisasie in staat stel om sy dienste en inisitiewe doeltreffend te verander om te pas by hierdie behoeftes. Die implikasies daarvan om die hervertolking van hierdie temas te ignoreer kan lei tot die gebruik van ontoepaslike en onbehulpsame maatreëls wat die numeriese kwantifikasie van gehalte behels deur teikens en om onmoontlike verwagtings te skep by burgers, wat lei tot frustrasie en ontevredenheid. Die implementering van skaars vervaardigingsbeginsels moet begin deur die konteks waarbinne staatsentiteite funksioneer, te verstaan en te bepaal. Die konteks van ’n organisasie sluit in faktore soos die organisasie se struktuur, kultuur, strategiese doelwitte en belanghebbers, tesame met wetlike en ander vereistes, wat belangrik is wannneer die implimentering van skaars vervaardigingsbeginsels oorweeg word.; Yiba nomfanekisongqondweni woMzantsi Afrika apho amaqumrhu karhulumente (iiSOE) angaqhubeli phambili nje ukukhulisa uqoqosho kodwa enikezela ngeenkonzo ezigqibeleleyo kubemi, ngelixa esebenza ngokufanelekileyo nangokuzinzileyo. Ngelishwa, lo mbono okwangoku unyhashwa yimiba yolawulo, ulawulo olugwenxa, kunye nenkcitho kwiiSOE. Nangona kuninzi okuye kwafunyaniswa malunga nemveliso yokunciphisa inkcitho njengendlela ethembisa ukunciphisa inkcitho kunye nokuphucula indlela yokusebenza, uphuhliso lwezikhokelo ngezikhokelo zemveliso yokunciphisa inkcitho luveze umsantsa othile. Umsantsa wokuqala kukuba akukho nasinye isikhokelo esiphakanyisiweyo kuphononongo loncwadi olusetyenzisiweyo kuphando esibonelela ngokulungelelaniswa kwemigaqo yokunciphisa inkcitho kwicandelo likarhulumente. Umsantsa wesibini lutyekelo oluthe lwahlolwa olubonakalayo kwindlela yolawulo esuka kwabaphetheyo eya kubemi phakathi kwezikhokelo zemveliso yokunciphisa inkcitho. Olu tyekelo, nangona lufanelekile kwiimeko ezithile, lunokujongana nemiqobo xa luphunyezwa kwimeko yeeSOE eMzantsi Afrika. Ngokusekelwe kwiimbono ezisuka kwingcingane yendlela yolawulo ngokwemeko (icontingency theory), olu phando lubonise uncedo kunye nemiqobo eyayanyaniswa nokusetyenziswa kwemigaqo yemveliso yokunciphisa inkcitho kwiiSOE zoMzantsi Afrika. Umphandi uphonononge ukusebenzisana okucwangcisiweyo kwemigaqo engqingqwa yokunciphisa inkcitho ngaphakathi kwimeko yeSOE ngokusebenzisa inkalo yengcingane yolawulo olucwangcisiweyo ye-viable systems theory (iVST). Olu phando ngoko ke lwandlale ingxoxo yokuphuhlisa isikhokelo esisebenzayo sokunciphisa inkcitho esilungele ukuqubulisana kwakhona nemigaqo nengcamago yokunciphisa inkcitho ngokohlobo olulodwa kwicandelo likarhulumente. IShedyuli yesi2 yeeSOE eMzantsi Afrika ibandakanye abantu ekujoliswe kubo kolu phando. Isampulu yophandontyilazwi ibinabathathinxaxheba abali10 kwiziko ngalinye. Kuphononongwe intsebenziswano ecwangcisiweyo yemigaqo yokunciphisa inkcitho ngokwakwimeko yeeSOE ngokwembono yeVST kunye nengcingane yendlela yolawulo ngokwemeko, eyondlala ingxoxo yesikhokelo esibonisa ukuba kuyenzeka ukulungelelanisa imigaqo yokunciphisa inkcitho kwiiSOE zokudala imveliso enexabiso kunye nokunciphisa inkcitho. Kusetyenziswe indlela yophandontyilazwi kwindlela yokufumana ubunzulu obungakumbi ngokukhangela amava neengcamango zomxholo othile wezentlalo ukuphanda iiSOE ezintathu zeShedyuli yesi2. Kukhethwe abathathinxaxheba abangamashumi amathathu ngenjongo yodliwanondlebe olucwangciswe mayane lwangeintanethi. Kufunyaniswe ukuba ukudalwa kwemveliso enexabiso ziinkokheli zequmrhu kufuna intathonxaxheba yabo ababandakanyekayo bangaphakathi nabangaphandle. Kubalulekile ukuba nenkxaso yababandakanyekayo ababalulekileyo bangaphandle, kubandakanywa urhulumente, amahlakani, abasebenzisi bemveliso, amaqela anomdla, kunye nabaxhasi/abanikeli, ukudala imveliso enexabiso ngempumelelo. Ngokubonisana nababandakanyekayo, iinkokheli zequmrhu zinokufumana ulwazi ngeemfuno kunye nokulindelekileyo kubathengi belo qumrhu, olunozenza ukuba zilungelelanise iinkonzo namaphulo alo okuhlangabezana nezi mfuno ngempumelelo. Iziphumo zokungahoyi ukuqubulisana kwakhona nale mixholo zinokukhokelela ekusetyenzisweni kwemilinganiselo engafanelekanga okanye engancedisiyo ebandakanya ubungakanani ngokwamanani bomgangatho koko ekujoliswe kuko nokudala ukuba abemi balindele okungenakwenzeka, okukhokelela emsindweni nasekunganelisekeni kwabo. Ukuphunyezwa kwemigaqo yemveliso yokunciphisa inkcitho kufuneka kuqale ngokuqonda kunye nokufumanisa imeko iiSOE ezisebenza phantsi kwayo. Imeko yequmrhu ibandakanya izinto ezifana nolwakhiwo lwequmrhu, inkqubo, iinjongo zobuchule, nababandakanyekayo, uwisomthetho nezinye iimfuneko, ezibalulekileyo xa kuqwalaselwa ukuphunyezwa kwemigaqo yemveliso yokunciphisa inkcitho. Abstracts in English, Afrikaans and IsiXhosa 2024-02-02T00:00:00Z https://ir.unisa.ac.za/handle/10500/31620 Investigating the influence of first-year expectations and experiences on student academic performance Booi, Elizabeth Mmapholo This study examines the impact of first-year university students’ expectations and experiences on their academic performance to enable early strategic interventions. The research is grounded in various theoretical frameworks, including Astin’s theory of student involvement, Gardner’s transition theory, Tinto’s theory of student departure and Lizzio’s framework of five senses of success, providing a comprehensive understanding of the transition of students to university life. The study follows a six-step Cross-Industry Standard Process for Data Mining (CRISP-DM). It involves data profiling of student demographics, academic attributes, expectations and experiences from a sample dataset of 2 054 records at the University of the Western Cape, South Africa. Key findings reveal differences in academic performance across different demographics, with financial support significantly affecting outcomes. Factor analysis identified latent factors such as effective learning, social well-being, academic support, and access to information. The study found that the student performance models were not sufficiently robust for accurate predictions, with F1-scores below 60%. In contrast, academic outcome models, especially the random forest model, showed more promise, with F1-scores above 70%. Recommendations focus on targeted interventions, comprehensive orientation, enhanced academic support, and fostering an environment for social well-being. The study highlights the need for a multifaceted approach to student support, emphasising regular monitoring, evaluation and adaptability in interventions to create a supportive academic environment.; Hierdie studie doen ondersoek na die impak van eerstejaaruniversiteit-studente se verwagtinge en ervarings op hul akademiese prestasie ten einde tydige strategiese ingrypings te aktiveer. Die navorsing is op verskeie teoretiese raamwerke gegrond, wat insluit Astin se teorie van studentebetrokkenheid, Gardner se oorgangsteorie, Tinto se teorie oor studente wat opskop en Lizzio se suksesraamwerk van vyf gewaarwordinge. Die navorsing bied dus ’n omvattende begrip van studente se oorgang tot universiteitslewe. Die studie volg ’n ses-stap, kruisindustrie standaard proses vir dataontginning (Cross-Industry Standard Process for Data Mining [CRISP-DM]). Dit behels die datasamestelling van studentedemografie, akademiese eienskappe, verwagtinge en ervarings uit ’n steekproefdatastel van 2 054 rekords van studente aan die Universiteit van Wes-Kaapland, Suid-Afrika. Deurslaggewende bevindinge dui op verskille in akademiese prestasie oor verskillende demografie¨e heen, met finansi¨ele steun wat die uitkomste beduidend affekteer. Faktoranalise het latente faktore soos effektiewe leer, maatskaplike welstand, akademiese ondersteuning en toegang tot inligting ge¨ıdentifiseer. Die studie het bevind dat studenteprestasiemodelle nie sterk genoeg was vir akkurate voorspellings nie. F1-tellings was laer as 60%. Daarteenoor was die akademiese-uitkomstemodelle, veral die ewekansige bosmodel met F1-tellings van ho¨er as 70% meer belowend. Aanbevelings fokus op gerigte ingrypings, omvattende ori¨entasie, verhoogde akademiese ondersteuning en die kweek van ’n omgewing wat maatskaplike welstand bevorder. Die studie vestig die aandag op die behoefte aan ’n veelvlakkige benadering tot studenteondersteuning en lˆe klem op gereelde monitering, evaluering en plooibaarheid van ingrypings ten einde n ondersteunende akademiese omgewing daar te stel.; Patlisiso e e tlhatlhoba tshusumetso ya ditsholofelo tsa ngwaga wa ntlha wa dithuto wa baithuti ba yunibesithi gammogo le maitemogelo a bone a tiragatso ya seakademiki go ka ba kgontsha go dira ditogamaano go sa le gale. Patlisiso e e ikaegile mo matlhomesong a thuto a a mmalwa ao a akaretsang kgopolo ya Astin ya go nna le seabe ga baithuti, kgopolo ya phetogo ya Gardner, kgopolo ya Tinto ya go tsamaya ga baithuti, le letlhomeso la maikutlo a katlego a le matlhano la Lizzio, mme tsotlhe tse di tla tlamela ka kitso ya go tlhaloganya ka botlalo phetogo ya baithuti fa ba tsena mo botshelong jwa yunibesithi. Patlisiso e e latela magato a le marataro a Thulaganyo ya Tekanyetso ya Kgabaganyomadirelo ya Kepadatha (CRISP-DM). E akaretsa go dira porofaele ya datha ya palo ya baithuti, dinonofo tsa seakademiki, ditsholofelo le maitemogelo go tswa seteng ya datha ya tseosekao ya direkoto di le 2 054 tsa kwa Yunibesithing ya Kapa Bophirima, Aforika Borwa. Diphitlhelelo tse di botlhokwa di senola dipharologanyo magareng ga tiragatso ya seakademiki go kgabaganya dipalo tsa baithuti tse di farologanyeng, le tshegetso ya matlole eo e amang dipoelo segolo. Tlhatlhobo ya dintlha e supile dintlha tse di fitlhegileng jaaka go ithuta sentle, boitekanelo jwa loago, tshegetso ya seakademiki, le phitlhelelo ya tshedimosetso. Patlisiso e e fitlhetse gore dikao tsa tiragatso ya baithuti di ne di sa nonofela ponelopele e e tlhomameng, ka maduo a F1 a a ka tlase ga 60%. Mo pharologanyong, dikao tsa dipoelo tsa seakademiki, segolojang sekao sa random forest, se supile tshepiso e nngwe gape, ka maduo a F1 a a kwa godimo ga 70%. Dikatlanegiso di tsepamisa mogopolo mo ditsereganyong tse di lebilweng, molebo ka botlalo, tshegetso e e tokafaditsweng ya seakademiki, gammogo le kgodiso ya maemo a boitekanelo jwa loago. Patlisiso e tlhagisa tlhokego ya mokgwa wa dikarolo di le dintsi tsa tshegetso ya baithuti, go gatelela tekolo ya nako le nako, go tlhatlhoba le go fetofetoga ga ditsereganyo go tlhola maemo a tshegetso a seakademiki. Text in English, abstracts in English, Afrikaans and Tswana 2024-01-01T00:00:00Z https://ir.unisa.ac.za/handle/10500/31537 Exploring the accuracy-explainability trade-off on credit scoring classifiers Mtiyane, Sibusiso Recent research has highlighted the significance of accuracy and explainability of classification models applied across various disciplines. A wide range of classification models and combinations of models have been extensively studied to determine those with superior performance. These studies demonstrate that models that tend to be more accurate are also difficult to understand; there appears to be a trade-off between accuracy and explainability. Consequently, this has led to an increased focus on explainable artificial intelligence, a field of research concerned with explaining model predictions. Although explainable artificial intelligence is an area of research with growing popularity in the science community, there are still limited case studies that explore its applications in credit default risk. Credit default risk refers to the potential financial loss or risk that is incurred by a credit provider when an obligor fails to meet their debt obligations. To quantify, mitigate and manage the risk associated with granting credit proactively, credit providers utilise scoring classifiers to assess the risk of credit applicants prior to granting credit. Furthermore, credit risk providers are legally required to explain predictions of scoring classifiers. Popular classifiers used in credit risk include logistic regression, discriminant analysis, decision trees, random forests, bootstrap aggregation, neural networks, support vector machines and gradient boosting algorithms. Logistic regression and discriminant analysis are widely adopted in the financial industry because they perform reasonably well and are inherently interpretable. However, these approaches are giving way to alternative approaches that offer improved accuracy in risk assessment, even though these alternatives lack interpretability; they are less comprehensible and are often regarded as black boxes. This lack of interpretability has resulted in a reluctance to adopt these alternative techniques in credit granting. The aim of this study is to remove the aforementioned barrier of using black box models by utilising explainable artificial intelligence methods, such as Shapley additive explanations and local interpretable model-agnostic explanations. The study also examines the accuracy-explainability trade-off of different classifiers by developing and evaluating eight classification models on two publicly available credit datasets. Eight classification models were constructed, including decision trees, logistic regression, linear discriminant analysis, support vector machines, artificial neural networks, bootstrap aggregation, random forest, and light gradient boosting classifier. Their performance and interpretability were assessed after training and tuning the hyperparameters for optimal comparison on training, testing and validation subsets of the data. Performance accuracy was measured using the area under the curve on 30 random subsets generated from the validation data. Furthermore, the Kruskal Wallis test and Dunn’s multi-comparison test were used to rank the predictive models by accuracy and to determine if the differences in mean accuracy are statistically significant. The interpretability of these classifiers was conducted for both transparent and black box models. To achieve these ends, key preprocessing steps were developed to reduce the complexities of local and global model interpretation. In addition, Shapley additive explanations and local interpretable model-agnostic explanations were utilised to analyse the relative importance of features and the impact on predictions. The experiments show that the artificial neural network, ensembles and other treebased algorithms significantly outperform logistic regression and linear discriminant analysis in the first case study. However, contradictory results are obtained for the second case study, as the performance of the classifiers are relatively comparable. This indicates that model performance depends on the data from which the models are constructed. These two case studies show that the perceived trade-off between accuracy and explainability does not always hold true. Furthermore, Shapley additive explanations yielded results that are consistent with the intrinsic interpretability results of the transparent methods. This post-hoc interpretability enables us to understand how the predictions are made and what factors contributed to the prediction. This is important to create a reliable and trustworthy framework that uses black box models for credit decisions. The research highlights the benefits of using alternative methods for credit risk scoring, showing that the performance can vary significantly. It also demonstrates the effectiveness of Shapley additive explanations and local interpretable modelagnostic explanations to explain predictions of black box classifiers. However, it identifies challenges in using the Shapley additive explanations. The mean absolute value may be sensitive to outliers, which could have an impact on feature importance. Therefore, further work is required to enhance the efficiency of calculating Shapley additive explanations’ values for linear classifiers and some ensembles.; Onlangse navorsing het die belangrikheid uitgelig van die akkuraatheid en verduidelikbaarheid van klassifikasiemodelle wat dwarsoor verskeie dissiplines toegepas word. ’n Wye reeks klassifikasiemodelle en modelkombinasies is omvattend bestudeer om daardie modelle met voortreflike prestasie te bepaal. Hierdie studies het gedemonstreer dat modelle wat neig om meer akkuraat te wees, ook moeilik is om te verstaan; dit kom voor of daar ’n kompromie is tussen akkuraatheid en verduidelikbaarheid. Dit het gevolglik aanleiding gegee tot ’n verhoogde fokus op verduidelikbare kunsmatige intelligensie, ’n navorsingsveld wat met die verduideliking van modelvoorspellings gemoeid is. Alhoewel verduidelikbare kunsmatige intelligensie ’n navorsingsgebied is wat besig is om in gewildheid toe te neem binne die wetenskapgemeenskap, is daar steeds beperkte gevallestudies wat die toepassing daarvan op kredietwanbetalingsrisiko ondersoek. Kredietwanbetalingsrisiko verwys na die potensi¨ele finansi¨ele verlies of risiko waaraan ’n kredietverskaffer blootgestel word wanneer ’n skuldenaar in gebreke bly om hul skuldverpligtinge na te kom. Ten einde die risiko wat met kredietverskaffing geassosieer word proaktief te kwantifiseer, versag en bestuur, moet kredietverskaffers kredietgraderingsklassifiseerders gebruik om die moontlike risiko te evalueer wat kredietaansoekers inhou, voordat krediet toegestaan word. Voorts is kredietrisikoverskaffers volgens wet verplig om die voorspellings van kredietgraderingsklasifiseerders te verduidelik. Gewilde klassifiseerders wat in kredietrisiko gebruik word, sluit logistieke regressie, diskriminantanalise, besluitnemingsbome, ewekansige woude, skoenlussamevoeging, neurale netwerke, ondersteuningsvektormasjiene en gradi¨entversterkingsalgoritmes in. Logistieke regressie en diskriminantanalise is algemeen deur die finansi¨ele bedryf aanvaar aangesien hulle redelik goed presteer en inherent verduidelikbaar is. Hierdie benaderings skep egter ruimte vir alternatiewe benaderings wat verbeterde akkuraatheid ten opsigte van risiko-assessering bied selfs al gaan hierdie alternatiewe benaderings mank aan interpreteerbaarheid; hulle is nie so verstaanbaar nie en word dikwels as swartkissies (black boxes) gesien. Hierdie gebrek aan interpreteerbaarheid het tot gevolg dat daar ’n traagheid is om hierdie alternatiewe kredietverleningstegnieke aan te neem. Hierdie studie het ten doel om die voorafgenoemde versperring tot die gebruik van swartkissiemodelle te verwyder deur verduidelikbare kunsmatige intelligensiemetodes soos Shapely se additiewe verduidelikings en plaaslike interpreteerbare model-agnostiese verklarings te gebruik. Die studie ondersoek ook die akkuraatheidverduidelikbaarheidskompromie van verskillende klassifiseerders deur agt klassifikasiemodelle vir twee openbaar beskikbare kredietdatastelle te ontwikkel en te evalueer. Agt klassifikasiemodelle is saamgestel, naamlik besluitnemingsbome, logistieke regressie, liniˆere diskriminantanalise, ondersteuningsvektormasjiene, kunsmatige neurale netwerke, skoenlussamevoeging, ewekansige woud en ligte gradi¨entversterkingsklassifiseerder. Hul prestasie en interpreteerbaarheid is geassesseer na opleiding en instelling van die hiperparameters vir optimale vergelyking van opleiding, toetsing en geldigverklaring van deelversamelings van die data. Prestasie-akkuraatheid is gemeet deur van die area onder die kurwe van 30 ewekansige deelversamelings wat uit die geldigverklaarde data gegenereer is, gebruik te maak. Voorts is daar van die Kruskal Wallis-toets en Dunn se multivergelykingstoets gebruik gemaak om die voorspellingsmodelle ten opsigte van akkuraatheid te klassifiseer en te bepaal of die verskille in gemidddelde akkuraatheid statisties beduidend is. Die interpreteerbaarheid van hierdie klassifiseerders is vir beide deursigtige en swartkassiemodelle uitgevoer. Om hierdie resultate te verkry, is belangrike voorverwerkingstappe ontwikkel om die kompleksiteite van plaaslike sowel as globale modelinterpretasie te verminder. Daarbenewens is Shapley se additiewe verduidelikings en plaaslike interpreteerbare model-agnostiese verduidelikings ook ingespan om die relatiewe belangrikheid van kenmerke en die impak op voorspellings te ontleed. Die eksperimente toon dat die kunsmatige neurale netwerk, ensembles en ander boomgebaseerde algoritmes in die eerste gevallestudie beduidend beter as die logistieke regressie en liniˆere diskriminantanalise presteer het. Die tweede gevallestudie het egter teenstrydige resultate opgelewer. In die tweede gevallestudie is die prestasie van die klassifiseerders relatief vergelykbaar. Dit is ’n aanduiding dat modelprestasie afhanklik is van die data waaruit die modelle saamgestel is. Hierdie twee gevallestudies toon dat die waargenome kompromie tussen akkuraatheid en verduidelikbaarheid nie altyd waar is nie. Boonop het die Shapley additiewe verduidelikings resultate opgelewer wat met die intrinsieke interpreteerbaarheidsresultate van die deursigtige metodes ooreenstem. Hierdie post-hoc interpreteerbaarheid help ons om te verstaan hoe die voorspellings gemaak word en watter faktore tot die voorspellings bygedra het. Laasgenoemde is belangrik ten einde ’n betroubare en geloofwaardige raamwerk te skep wat van swartkassiemodelle vir kredietbesluite gebruik maak. Die navorsing beklemtoon die voordele van die gebruik van alternatiewe metodes vir kredietrisikogradering; dit toon dat die prestasie aansienlik kan varieer. Dit demonstreer ook die doeltreffendheid van die Shapley additiewe verduidelikings en plaaslike interpreteerbare model-agnostiese verduidelikings in die verduideliking van voorspellings van swartkissieklassifiseerders. Dit is egter so dat dit uitdagings ten opsigte van die Shapley additiewe verduidelikings identifiseer. Die gemiddelde absolute waarde mag dalk sensitief wees vir uitskieters wat ’n impak op die belangrikheid van kenmerke kan hˆe. Daarom is verdere werk nodig om die doeltreffendheid van die berekening van Shapley se additiewe verduidelikings se waardes vir liniˆere klassifiseerders en sommige ensembles te versterk.; Diphuputso tsa morao tjena di totobaditse bohlokwa ba ho nepahala le ho hlaloswa ha mefuta ya dihlopha e sebediswang dikarolong tse fapaneng. Mefuta e mengata e fapaneng ya dihlopha le motswako wa mefuta e nnile ya ithutwa haholo ho fumana hore na ke efe e nang le tshebetso e phahameng. Diphuputso tsena di bontsha hore mehlala e atisang ho nepahala haholwanyane le yona e thata ho e utlwisisa; ho bonahala ho e na le kgwebo pakeng tsa ho nepahala le ho hlalosa. Ka lebaka leo, sena se lebisitse tlhokomelong e eketsehileng ho bohlale bo hlakileng ba maiketsetso, lefapha la dipatlisiso le amanang le ho hlalosa dikgakanyo tsa mohlala. Leha bohlale ba maiketsetso bo hlaloswang e le sebaka sa dipatlisiso se ntseng se hola setumo se ntseng se hola setjhabeng sa mahlale, ho ntse ho na le dithuto tse fokolang tse hlahlobang tshebediso ya yona kotsing ya ho se be teng ha mekitlane. Kotsi ya ho se be teng ha mokitlane e bolela tahlehelo ya ditjhelete e ka bang teng kapa kotsi e hlahiswang ke mofani wa mokoloto ha motho ya tlamang a hloleha ho fihlela mekoloto ya hae. Ho lekanya, ho fokotsa le ho laola kotsi e amanang le ho fana ka mokoloto ka potlako, bafani ba mekitlane ba sebedisa dihlopha tsa dintlha ho lekola kotsi ya bakopi ba mekitlane pele ba fana ka mokoloto. Ho feta moo, bafani ba kotsi ya mokoloto ba hlokwa ka molao ho hlalosa dikgakanyo tsa dihlopha tsa dintlha. Dihlopha tse tsebahalang tse sebediswang e le kotsi ya mokoloto di kenyelletsa ho theola maemo, hlahlobo ya kgethollo, difate tsa diqeto, meru e sa rerwang, pokello ya bootstrap, marangrang a neural, metjhini ya divector ya tshehetso le dialgorithms tse matlafatsang. Phokotso ya dintho le hlahlobo ya kgethollo di amohelwa haholo indastering ya ditjhelete hobane di sebetsa hantle ka mokgwa o utlwahalang mme ka tlhaho di ka tolokwa. Leha ho le jwalo, mekgwa ena e fana ka mokgwa wa mekgwa e meng e fanang ka ho nepahala ho ntlafetseng ha ho hlahlojwa kotsi, le hoja mekgwa ena e meng e se na tlhaloso; ha di utlwisisehe mme hangata di nkwa e le mabokose a matsho. Kgaello ena ya hlaloso e bakile ho qeaqea ho sebedisa mekgwa ena e meng ya ho fana ka mekoloto. Sepheo sa thuto ena ke ho tlosa mokwallo o boletsweng ka hodimo wa ho sebedisa mehlala ya diblackbox ka ho sebedisa mekgwa e hlakileng ya bohlale ba maiketsetso, jwalo ka dihlaloso tsa tlatsetso tsa Shapley le dihlaloso tsa sebaka sa habo bona tsa agnostic. Boithuto bona bo boetse bo hlahloba kgwebo e nepahetseng le hlaloso e nepahetseng ya dihlopha tse fapaneng ka ho theha le ho lekola mefuta e robedi ya dikarolo ho didatabase tse pedi tse fumanehang phatlalatso ya tsa mekoloto. Ho ile ha ahwa mefuta e robedi ya dikarolo, ho kenyeletswa lifate tsa liqeto, ho theoha ha thepa, hlahlobo ya kgethollo e tshwanang, metjhini ya divector tse tshehetsang, marangrang a maiketsetso a neural, aggregation ya bootstrap, moru o sa rerwang, le sehlopha se matlafatsang se bobebe. Tshebetso ya bona le hlaloso ya bona di ile tsa hlahlojwa ka mora ho kwetliswa le ho lokisa di-hyperparameters bakeng sa papiso e nepahetseng mabapi le kwetliso, diteko le ho netefatsa dikarolwana tsa data. Ho nepahala ha tshebetso ho ile ha lekanyetswa ho sebediswa sebaka se ka tlasa lekgalo ho disubsets tse 30 tse sa rerwang tse hlahisitsweng ho data ya netefatso. Ho feta moo, teko ya Kruskal Wallis le ya Dunn ya ho bapisa dintho tse ngata di ile tsa sebediswa ho beha maemo a ponelopele ka ho nepahala le ho fumana hore na diphapano tsa ho nepahala ha moelelo di bohlokwa ho latela dipalo. Hlaloso ya dihlopha tsena e ile ya etswa bakeng sa mehlala ya dibox tse bonaletsang le tse ntsho. Ho finyella diphello tsena, mehato ya bohlokwa ya ho lokisa esale pele e ile ya ntlafatswa ho fokotsa ho rarahana ha hlaloso ya mohlala ya lehae le ya lefatshe. Ntle le moo, dihlaloso tsa tlatsetso tsa Shapley le dihlaloso tsa sebaka sa sebaka sa motlolo wa agnostic di ile tsa sebediswa ho sekaseka bohlokwa bo lekanyeditsweng ba dikarolo le phello ya dikgakanyo. Diteko di bontsha hore marangrang a maiketsetso a methapo ya kutlo, di-ensembles le di-algorithms tse ding tse thehilweng sefateng di feta haholo ho theoha ha thepa le hlahlobo e fapaneng ya kgethollo thutong ya pele. Leha ho le jwalo, diphetho tse hanyetsanang di fumanwa bakeng sa thuto ya mohlala ya bobedi, kaha tshebetso ya dihlopha di batla di bapiswa. Sena se bontsha hore tshebetso ya mohlala e itshetlehile ka data eo mehlala e ahilweng ho yona. Dithuto tsena tse pedi tsa dinyewe di bontsha hore phapang pakeng tsa ho nepahala le ho hlalosa ha se kamehla e leng nnete. Ho feta moo, dihlaloso tsa tlatsetso tsa Shapley di hlahisitse ditholwana tse tsamaellanang le sephetho sa ho toloka ha mekgwa e pepeneneng. Hlaloso ena ya post-hoc e re thusa ho utlwisisa hore na dikgakanyo di etswa jwang le hore na ke dintlha dife tse tlatseditseng ho bolela esale pele. Sena ke sa bohlokwa ho theha moralo o ka tsheptjwang le o ka tsheptjwang o sebedisang mehlala ya lebokose le letsho bakeng sa diqeto tsa mokitlane. Patlisiso e totobatsa melemo ya ho sebedisa mekgwa e meng bakeng sa dintlha tsa kotsi ya mokoloto, e bontsha hore tshebetso e ka fapana haholo. E boetse e bontsa katleho ya dihlaloso tsa tlatsetso ya Shapley le dihlaloso tsa sebaka seo ho ka tolokwang tsa mohlala-agnostic ho hlalosa dikgakanyo tsa dihlopha tsa diblackbox. Leha ho le jwalo, e supa mathata a ho sebedisa dihlaloso tsa tlatsetso ya Shapley. Theko ya boleng bo felletseng e kanna ya ameha ho barekisi ba kantle, e ka amang bohlokwa ba karolo. Ka hona, mosebetsi o mong o a hlokahala ho ntlafatsa bokgoni ba ho bala boleng ba dihlaloso tsa tlatsetso tsa Shapley bakeng sa dihlopha tsa linear le diensembles tse ding. Text in English with summaries in Afrikaans and Tswana 2024-02-01T00:00:00Z