THE VI INTERNATIONAL SCIENTIFIC CONFERENCE “SCIENTIFIC FOUNDATIONS FOR THE USE OF
INFORMATION TECHNOLOGIES OF A NEW LEVEL AND MODERN PROBLEMS OF AUTOMATION”,
NOVEMBER 20, 2025
201
A MULTI-CRITERIA DECISION ANALYSIS (MCDA)-BASED
EVALUATION MODEL FOR PERSONALIZED LEARNING
PLATFORMS IN HIGHER EDUCATION
Za ipo a Mukaddas Djumayozo na1, Abdilamiye a Noila Ramiddino na2
1Associa e P o esso , Depa men o Compu e and So wa e Enginee ing
Te mez S a e Uni e si y, Uzbekis an;
21s -Yea Mas e ’s S uden , Majo in Compu e Sys ems and So wa e Enginee ing
Te mez S a e Uni e si y, Uzbekis an
h ps://doi.o g/10.5281/zenodo.17739858
Abs ac . In ecen yea s, he apid in eg a ion o a i icial in elligence and adap i e
echnologies in o highe educa ion has accele a ed he shi owa d pe sonalized lea ning.
Howe e , despi e he p oli e a ion o pla o ms such as ALEKS, Knew on Al a, Sma Spa ow,
Realizei , and Cou se a, he e emains a lack o comp ehensi e e alua ion models ha can
sys ema ically compa e hei pedagogical, echnical, and usabili y e ec i eness. This s udy
p oposes a Mul i-C i e ia Decision Analysis (MCDA)-based e alua ion model o assess he
o e all pe o mance o pe sonalized lea ning pla o ms ac oss en key c i e ia, including adap i e
algo i hms, lea ning analy ics, use in e ac i i y, ins uc o in ol emen , echnical in eg a ion,
da a secu i y, and cos -e iciency. The esea ch adop s a mixed-me hod app oach, combining
quali a i e con en analysis and quan i a i e sco ing based on a i e-poin Like scale. The
collec ed da a we e analyzed h ough weigh ed agg ega ion o calcula e he in eg a ed e iciency
index (Ip) o each pla o m. Findings e eal ha Realizei achie ed he highes o e all sco e
(4.6/5), demons a ing s ong AI-d i en adap abili y and supe io LMS in eg a ion. ALEKS
anked second (4.1/5) due o i s e ec i e gap-analysis algo i hm, while Cou se a showed he
lowes adap abili y index (3.6/5), mainly due o limi ed pe sonaliza ion dep h. The p oposed
MCDA-based model p o ides a sys ema ic and eplicable amewo k o decision-make s in
highe educa ion ins i u ions o selec , implemen , and e alua e digi al lea ning pla o ms
e ec i ely.
Keywo ds. Pe sonalized Lea ning; Adap i e Lea ning; Highe Educa ion; Mul i-C i e ia
Decision Analysis (MCDA); Lea ning Analy ics; A i icial In elligence; Digi al In eg a ion
In oduc ion
In ecen yea s, he apid ad ancemen o a i icial in elligence (AI) and digi al
echnologies has signi ican ly ans o med he landscape o educa ion, gi ing ise o a new phase
in pe sonalized lea ning. This app oach enables he c ea ion o indi idualized lea ning pa hways
ailo ed o each s uden 's knowledge le el, lea ning s yle, and in e es s. In highe educa ion,
pe sonalized lea ning plays a i al ole in imp o ing academic pe o mance, enhancing
independen hinking, and os e ing analy ical compe encies among s uden s.
The ele ance o his s udy lies in he need o iden i y which pe sonalized lea ning
pla o ms cu en ly used in highe educa ion p o ide he mos e ec i e lea ning expe iences unde
he condi ions o digi al ans o ma ion. The e o e, his esea ch conduc s a compa a i e analysis
o widely adop ed pla o ms (ALEKS, Knew on (Al a), Sma Spa ow, Realizei , and Cou se a)
o e alua e hei e ec i eness ac oss mul iple dimensions, including adap i e algo i hms, lea ning
THE VI INTERNATIONAL SCIENTIFIC CONFERENCE “SCIENTIFIC FOUNDATIONS FOR THE USE OF
INFORMATION TECHNOLOGIES OF A NEW LEVEL AND MODERN PROBLEMS OF AUTOMATION”,
NOVEMBER 20, 2025
202
analy ics capabili ies, use expe ience (s uden and ins uc o in e aces), ins uc o ole and
pedagogical managemen ools, echnical in eg a ion (LMS, SSO, API), and da a secu i y.
Th ough his compa a i e e alua ion, he s udy aims o iden i y he mos sui able pla o ms
and de elop e idence-based ecommenda ions o op imizing pe sonalized lea ning p ocesses,
moni o ing academic pe o mance, suppo ing ins uc o s, and implemen ing digi al in as uc u e
in highe educa ion ins i u ions.
The indings o his esea ch a e expec ed o suppo s a egic digi al decision-making
wi hin uni e si ies by enabling e icien esou ce alloca ion, mode niza ion o cu icula and
eaching me hodologies, and he design o in eg a ion oadmaps compa ible wi h exis ing LMS
en i onmen s. Fu he mo e, he p oposed e alua ion c i e ia and i e-poin a ing amewo k no
only highligh he ela i e s eng hs and limi a ions o each pla o m bu also p o ide a
me hodologically g ounded basis o highe educa ion ins i u ions o make con ex ually
app op ia e and da a-d i en choices.
Li e a u e Re iew
In ecen yea s, pe sonalized lea ning — pa icula ly AI-d i en educa ional pla o ms —
has become a cen al opic in highe educa ion esea ch. S udies conduc ed be ween 2020 and 2025
ha e p ima ily ocused on h ee majo hemes: he e ec i eness o adap i e lea ning, he
pedagogical ole o ins uc o s, and he echnical in eg a ion o lea ning sys ems. Collec i ely,
hese wo ks highligh he ans o ma i e po en ial o adap i e lea ning echnologies while also
e ealing c i ical gaps in hei empi ical alida ion and implemen a ion p ac ices.
C. Me ino-Campos (2025) examined he impac o AI-based pe sonalized lea ning sys ems
in highe educa ion h ough a sys ema ic e iew o 45 academic sou ces. The s udy ound ha
such sys ems enhance s uden mo i a ion and imp o e he p ecision o assessmen s, al hough
challenges ela ed o empi ical alida ion and echnical in eg a ion emain un esol ed [1].
Simila ly, S. Saleem e al. (2025) su eyed uni e si y ins uc o s o explo e he adop ion o
pe sonalized lea ning ools, inding ha while hese sys ems inc ease s uden engagemen ,
insu icien digi al eadiness among ins uc o s limi s hei e ec i e u iliza ion [2].
F om a digi al compe ency pe spec i e, H. Yaseen (2025) demons a ed ha highe le els
o digi al li e acy among s uden s co ela e wi h g ea e bene i s om adap i e lea ning
en i onmen s [3]. W. S ielkowski (2025) ex ended his discussion by si ua ing adap i e lea ning
wi hin he amewo k o sus ainable educa ion, emphasizing i s abili y o indi idualize lea ning,
enable eal- ime moni o ing, and suppo da a-in o med eaching p ac ices [4].
Technological ad ances we e also explo ed by P. Shi e al. (2025), who applied deep
lea ning algo i hms o de elop an adap i e model o eaching his o y. Thei expe imen al s udy
e ealed ha s uden s using adap i e me hods ou pe o med hose in adi ional ins uc ion [5]. On
he o he hand, H. Ha is (2024) analyzed eache s’ pe cep ions o AI and adap i e sys ems,
iden i ying bo h op imism owa d pedagogical e iciency and conce ns abou educed ins uc o
agency and academic in eg i y [6].
Ac oss hese s udies, consis en indings indica e ha pe sonalized lea ning echnologies
can signi ican ly imp o e s uden ou comes, lexibili y, and analy ical dep h. Howe e ,
me hodological di e si y — including su eys, me a-analyses, and expe imen al app oaches —
has led o agmen ed insigh s ac oss pedagogical, echnical, and psychological domains.
A syn hesis o he e iewed li e a u e e eals ha se e al dimensions o pe sonalized
lea ning emain unde explo ed:
Ins uc o Role: Cu en esea ch p o ides limi ed insigh in o how ins uc o s in e ac wi h
THE VI INTERNATIONAL SCIENTIFIC CONFERENCE “SCIENTIFIC FOUNDATIONS FOR THE USE OF
INFORMATION TECHNOLOGIES OF A NEW LEVEL AND MODERN PROBLEMS OF AUTOMATION”,
NOVEMBER 20, 2025
203
adap i e lea ning sys ems and how hei manage ial and acili a i e oles can be e ec i ely
modeled. As a esul , comp ehensi e amewo ks o assessing eache -media ed adap i e lea ning
emain insu icien .
Technical In eg a ion: Few s udies add ess he in e ope abili y o pla o ms wi h exis ing
ins i u ional sys ems such as LMS, API in as uc u es, and da a secu i y p o ocols. This gap
es ic s he sys ema ic e alua ion o echnological compa ibili y and in o ma ion low e iciency.
Use Expe ience: Resea ch on use in e ace design, usabili y, and mo i a ional ac o s o
s uden s and ins uc o s emains sca ce. Mo eo e , empi ical assessmen s o how use expe ience
di ec ly a ec s lea ning pe o mance a e limi ed.
The e o e, his s udy aims o add ess hese gaps by conduc ing a compa a i e e alua ion
o pe sonalized lea ning pla o ms in highe educa ion - ocusing on hei e ec i eness, echnical
in eg a ion, and use expe ience. By applying a s uc u ed, MCDA-based e alua ion amewo k,
his esea ch seeks o con ibu e a holis ic unde s anding o adap i e lea ning ecosys ems and
in o m e idence-based digi al ans o ma ion in highe educa ion.
Resea ch Me hodology
This s udy employed a mixed esea ch app oach, combining elemen s o bo h quali a i e
and quan i a i e analysis. Such an app oach makes i possible o comp ehensi ely examine he
e ec i eness o pe sonalized highe educa ion pla o ms om mul iple pe spec i es and acco ding
o a ious e alua ion c i e ia.
The da a we e collec ed om seconda y sou ces. The main sou ces included scien i ic
a icles published be ween 2020 and 2025, analy ical e iews in in e na ional jou nals, echnical
documen a ion o he pla o ms (ALEKS, Knew on Al a, Sma Spa ow, Realizei , and Cou se a),
and use expe ience epo s. In addi ion, open-access epo s om uni e si ies ha ha e
implemen ed adap i e lea ning p ac ices we e also u ilized.
The esea ch sample was o med pu pose ully, ocusing on ma e ials di ec ly ela ed o he
esea ch opic and cha ac e ized by a high deg ee o academic eliabili y — such as a icles
published in in e na ionally indexed jou nals and o icial echnical o use documen a ion o he
pla o ms. The sample size was de e mined based on he analy ical dep h equi ed and he
ele ance o he ma e ials o he s udy objec i es.
The collec ed da a we e p ocessed using con en analysis and hema ic analysis me hods o
iden i y he main esea ch di ec ions and pa e ns.
I should be no ed, howe e , ha he s udy has se e al limi a ions. Only open-access
ma e ials published be ween 2020 and 2025 we e analyzed; due o he lack o empi ical
(expe imen -based) da a, some conclusions a e de i ed om seconda y e idence. Fu he mo e, as
he in e nal algo i hms o ce ain pla o ms ( o example, he code s uc u es o ALEKS and
Realizei ) a e no publicly a ailable, hei echnical aspec s we e assessed based on gene al
analy ical desc ip ions.
Despi e hese limi a ions, he chosen app oach made i possible o compa e pe sonalized
highe educa ion pla o ms om di e en pe spec i es and o iden i y hei ad an ages and
limi a ions in e ms o pedagogical e ec i eness, echnical in eg a ion, and use expe ience.
Resul s and Discussion
The esul s o he s udy we e de e mined h ough a compa a i e e alua ion o pe sonalized
highe educa ion pla o ms ac oss en key c i e ia — adap i e model/algo i hm (M₁), deg ee o
pe sonaliza ion (M₂), lea ning p ocess analy ics (M₃), lea ning pa hway design (M₄), in e ac i i y
and use expe ience (M₅), ins uc o ole and managemen capabili ies (M₆), echnical
THE VI INTERNATIONAL SCIENTIFIC CONFERENCE “SCIENTIFIC FOUNDATIONS FOR THE USE OF
INFORMATION TECHNOLOGIES OF A NEW LEVEL AND MODERN PROBLEMS OF AUTOMATION”,
NOVEMBER 20, 2025
204
in as uc u e and in eg a ion (M₇), da a secu i y (M₈), o e all e ec i eness (M₉), and p icing and
licensing model (M₁₀).
The e alua ion esul s a e p esen ed in Table 1, which comp ehensi ely e lec s he o e all
pe o mance indica o s o each pla o m.
Table 1.
E alua ion esul s based on c i e ia
№
C i e ia
ALEKS
Knew on
Al a
Sma
Spa ow
Realizei
Cou se a
M₁
Adap i e
model/algo i hm
5
4
4
5
3
M₂
Deg ee o
pe sonaliza ion
5
4
4
5
3
M₃
Lea ning p ocess
analy ics
4
4
4
5
3
M₄
Lea ning pa hway
4
4
4
5
3
M₅
In e ac i i y and use
expe ience
4
4
4
4
5
M₆
Ins uc o ole and
managemen
capabili ies
4
3
5
4
3
M₇
Technical
in as uc u e and
in eg a ion
4
4
3
5
3
M₈
Da a secu i y
4
4
3
5
4
M₉
O e all e ec i eness
4
4
4
5
3
M₁₀
P icing and licensing
model
3
4
3
4
5
A e age
sco e (Iₛ)
----
4.1
3.9
3.8
4.6
3.6
When analyzing he da a p esen ed in Table 1, i was ound ha he Realizei pla o m
achie ed he highes o e all sco e o 4.6, which can be a ibu ed o i s AI-d i en adap i e
adjus men algo i hms, eal- ime analy ics capabili ies, and a high deg ee o in eg a ion wi h LMS,
API, and da a secu i y sys ems. The ALEKS pla o m anked second wi h an a e age sco e o 4.1,
dis inguished by i s high p ecision in diagnosing lea ne s’ knowledge gaps and cons uc ing
indi idualized lea ning pa hways.
Knew on Al a (3.9) and Sma Spa ow (3.8) demons a ed mode a e pe o mance. Thei
s eng hs lie in in e ac i e engagemen wi h ins uc o s and adap i e con en gene a ion, hough
bo h pla o ms show limi a ions in e ms o echnical in eg a ion and da a p o ec ion. Cou se a
(3.6), despi e i s global e ec i eness, ecei ed a compa a i ely lowe sco e due o i s limi ed le el
o pe sonaliza ion.
Thus, he analysis esul s made i possible o sys ema ically compa e pe sonalized lea ning
pla o ms based on he Mul i-C i e ia Decision Analysis (MCDA) model. The sco es ob ained
h ough his app oach se ed as he basis o calcula ing he in eg a ed e iciency index (Iₛ) in he
subsequen s age.
THE VI INTERNATIONAL SCIENTIFIC CONFERENCE “SCIENTIFIC FOUNDATIONS FOR THE USE OF
INFORMATION TECHNOLOGIES OF A NEW LEVEL AND MODERN PROBLEMS OF AUTOMATION”,
NOVEMBER 20, 2025
205
In his s udy, a mul i-c i e ia in eg a ed e alua ion model was de eloped o assess
pe sonalized highe educa ion pla o ms. The o ma ion o his model is g ounded in he p inciples
o Mul i-C i e ia Decision Analysis (MCDA) [7,8] and he in eg a ed indexing app oach [9,10].
Th ough his amewo k, pe sonalized lea ning pla o ms we e comp ehensi ely e alua ed ac oss
pedagogical, echnical, and economic indica o s.
The pu pose o he model is o de e mine a single nume ical alue ep esen ing he o e all
e iciency o each pla o m by agg ega ing mul iple dimensions — pedagogical, echnical,
in e ac i e, and economic — in o a uni ied pe o mance index.
The e alua ion model is exp essed by he ollowing o mula:
=
=
n
i
ip M
n
I
1
1
(1)
whe e: Ip – he in eg a ed e iciency index o pla o m p; Mi – he sco e o c i e ion i ( anging
om 1 o 5); n – he o al numbe o c i e ia (in his s udy, n=10).
Each pla o m was e alua ed using a i e-poin Like scale, whe e 1 – poo , 2 – ai , 3 –
a e age, 4 – good, and 5 – excellen .
The ma hema ical essence o he model lies in he ac ha each pla o m’s e alua ions
ac oss all c i e ia a e exp essed as a no malized a e age alue. This app oach allows he
compa ison o di e en ypes o c i e ia wi hin a uni ied measu emen amewo k. Consequen ly,
he alue o Ip quan i a i ely e lec s he o e all e iciency o a pla o m on a scale om 1 o 5.
Thus, he e alua ion esul s p esen ed in Table 1 se e as he inpu da a o he p oposed
in eg a ed model. The inal Ip alue o each pla o m was calcula ed using he MCDA app oach,
and hese esul s we e subsequen ly analyzed in dep h in he sec ions on Scien i ic No el y and
P ac ical Signi icance.
This model has been applied o he i s ime o pe sonalized highe educa ion pla o ms
— ALEKS, Knew on Al a, Sma Spa ow, Realizei , and Cou se a — enabling a combined
analysis om pedagogical, echnical, and economic pe spec i es.
Whe eas p e ious s udies ypically ocused on ei he pedagogical o echnical aspec s in
isola ion, he p esen model p o ides a comp ehensi e assessmen encompassing mul iple
dimensions — adap i i y, lea ning analy ics, in e ac i i y, echnical in eg a ion, da a secu i y, and
economic e iciency.
The p ac ical signi icance o he esea ch lies in he ac ha he de eloped model allows
highe educa ion ins i u ions o scien i ically jus i y me hodological and analy ical decisions when
selec ing, implemen ing, and e alua ing digi al lea ning sys ems. The en-c i e ia e alua ion
amewo k (including adap i e model, ins uc o ole, use in e ace, echnical in eg a ion, da a
secu i y, and p icing) o e s uni e si ies an objec i e, e idence-based se o benchma ks o
pla o m selec ion.
Mo eo e , his app oach enables he o mula ion o ecommenda ions aimed a imp o ing
educa ional quali y, de eloping digi al in as uc u e, and enhancing academic pe o mance
moni o ing. In his way, he s udy p esen s a comp ehensi e model ha b idges he gap be ween
educa ional heo y and p ac ical implemen a ion in highe educa ion.
The analysis esul s indica e ha pe sonalized highe educa ion pla o ms di e
signi ican ly om one ano he , and hei o e all e iciency la gely depends on he quali y o
adap i e algo i hms, use expe ience, and he deg ee o echnical in eg a ion. The highes
in eg a ed e iciency index was obse ed in Realizei (Ip = 4.6). This esul can be explained by
THE VI INTERNATIONAL SCIENTIFIC CONFERENCE “SCIENTIFIC FOUNDATIONS FOR THE USE OF
INFORMATION TECHNOLOGIES OF A NEW LEVEL AND MODERN PROBLEMS OF AUTOMATION”,
NOVEMBER 20, 2025
206
he pla o m’s AI-d i en adap i e module, eal- ime lea ning analy ics capabili ies, and a obus
echnical in as uc u e ha ensu es seamless in eg a ion wi h LMS and API sys ems. The ALEKS
pla o m (Ip = 4.1) anked second, owing o i s Knowledge Space Theo y–based p ecision in
diagnosing lea ning gaps and i s s ong abili y o gene a e indi idualized lea ning pa hs.
Meanwhile, Knew on Al a and Sma Spa ow (Ip ≈ 3.8–3.9) demons a ed solid
pe o mance in adap i e con en c ea ion and ins uc o –s uden in e ac ion mechanisms, al hough
hei sco es we e lowe ed by limi a ions in echnical in eg a ion and da a secu i y. Cou se a (Ip =
3.6) — as a global lea ning pla o m — eaches a wide audience; howe e , he ela i ely limi ed
scope o i s pe sonalized lea ning algo i hms has educed i s o e all in eg a ed e iciency.
The e alua ion esul s also e ealed no iceable di e ences among he pla o ms in e ms
o ins uc o ole, echnical in eg a ion, and use expe ience. Fo ins ance, Realizei and ALEKS
p o ide ins uc o s wi h ad anced ools o ac i e moni o ing and indi idualized analy ics,
whe eas Cou se a and Sma Spa ow ely mo e hea ily on au oma ed p ocesses, limi ing eal-
ime ins uc o in e ac ion—an elemen ha di ec ly in luences he quali y o lea ning ou comes.
Findings de i ed om he MCDA-based model con i m ha he syne gy be ween
ins uc o in ol emen , adap i e algo i hms, and echnical in eg a ion se es as a key de e minan
in enhancing he e ec i eness o pe sonalized lea ning en i onmen s. These esul s a e consis en
wi h ea lie s udies ([1], [2], [8]), which demons a ed ha use engagemen , digi al li e acy, and
echnological adap abili y ha e a di ec impac on lea ning ou comes. Howe e , he dis inc
con ibu ion o he p esen esea ch lies in i s abili y o in eg a e pedagogical, echnical, and
economic indica o s in o a single composi e index, p o iding a uni ied e alua ion amewo k.
This in eg a i e app oach es ablishes a scien i ically g ounded decision-making ool o
highe educa ion ins i u ions, suppo ing he de elopmen o digi al ans o ma ion s a egies,
op imiza ion o lea ning managemen sys ems, and da a-d i en enhancemen o academic quali y.
Conclusion
The indings o his s udy demons a e ha he pedagogical, echnical, and economic
aspec s o pe sonalized highe educa ion pla o ms a e deeply in e connec ed. Acco ding o he
esul s ob ained h ough he Mul i-C i e ia Decision Analysis (MCDA) – based e alua ion model,
he Realizei pla o m achie ed he highes e iciency index, while ALEKS anked second o i s
accu acy in diagnosing knowledge gaps and gene a ing indi idualized lea ning pa hways.
Howe e , he analysis also e ealed ha Cou se a, Knew on Al a, and Sma Spa ow possess
ce ain limi a ions in e ms o ins uc o in ol emen , da a secu i y, and use expe ience.
The scien i ic conclusion de i ed om his s udy is ha enhancing he e ec i eness o
pe sonalized lea ning equi es he ha monious in eg a ion o adap i e algo i hms, in e ac i e
ins uc o engagemen , echnical in eg a ion, and da a secu i y mechanisms wi hin he pla o ms.
The MCDA-based in eg a ed e alua ion model success ully uni ied hese di e se c i e ia in o a
single quan i a i e indica o , allowing o a comp ehensi e assessmen o pla o m pe o mance.
The applica ion o his model p o ides highe educa ion ins i u ions wi h a scien i ically g ounded
ool o making da a-d i en decisions in he selec ion, e alua ion, and implemen a ion o digi al
lea ning sys ems.
F om a p ac ical pe spec i e, he model’s esul s can be u ilized in he ollowing ways:
To s anda dize pla o m selec ion c i e ia o uni e si ies (adap abili y, in eg a ion,
secu i y, cos );
To e alua e he e ec i eness o digi al lea ning sys ems h ough an in eg a ed index in
quali y moni o ing p ocesses;
THE VI INTERNATIONAL SCIENTIFIC CONFERENCE “SCIENTIFIC FOUNDATIONS FOR THE USE OF
INFORMATION TECHNOLOGIES OF A NEW LEVEL AND MODERN PROBLEMS OF AUTOMATION”,
NOVEMBER 20, 2025
207
To design a ge ed aining p og ams and me hodological ma e ials aimed a imp o ing
ins uc o s’ digi al compe encies;
To p o ide an analy ical ounda ion o educa ional policy de elopmen (e.g., wi hin he
amewo k o a Na ional Digi al Educa ion S a egy).
Thus, his esea ch is signi ican bo h heo e ically — by p oposing an in eg a ed
e alua ion model based on MCDA — and p ac ically, by o e ing a decision-making and
op imiza ion ool o he implemen a ion and imp o emen o digi al lea ning ecosys ems in highe
educa ion ins i u ions.
Recommenda ions and Fu u e P ospec s
The indings o his s udy indica e ha enhancing he e ec i eness o pe sonalized highe
educa ion pla o ms equi es he coo dina ed de elopmen o pedagogical, echnical, and da a
secu i y componen s. Acco dingly, he ollowing p ac ical ecommenda ions a e p oposed:
• Pedagogical In eg a ion: I is ecommended o implemen p o essional de elopmen
p og ams aimed a s eng hening ins uc o s’ digi al pedagogical compe encies o wo king wi h
pe sonalized lea ning pla o ms. This will enhance eache s’ ac i e pa icipa ion in adap i e
sys ems and imp o e hei impac on s uden s’ lea ning ou comes.
• Technical In eg a ion: To ensu e seamless in e ope abili y o pla o ms wi h LMS, API,
and Lea ning Analy ics sys ems, i is necessa y o de elop he na ional educa ional in o ma ion
in as uc u e based on an in eg a ed model.
• Use Expe ience (UX): A UX audi me hodology should be designed o imp o e
in e ace simplici y, isual design, and usabili y o bo h s uden s and ins uc o s.
• Da a Secu i y: Pla o ms should adop da a p o ec ion policies aligned wi h GDPR and
ISO 27001 s anda ds, wi h s onge enc yp ion and access con ol mechanisms o use
in o ma ion.
• Economic Aspec : I is ad isable o de elop inancing mechanisms based on eemium
o public–p i a e pa ne ship models o ensu e cos -e ec i e implemen a ion o highe educa ion
ins i u ions.
In e ms o u u e esea ch di ec ions, he ollowing pe spec i es a e iden i ied:
• Empi ical Tes ing: Conduc pilo s udies ac oss mul iple uni e si ies using he
de eloped MCDA model and analyze he ou comes;
• AI-D i en Adap i e Analysis: De elop a i icial in elligence models capable o
p edic ing s uden s’ pe o mance, mo i a ion, and lea ning engagemen ;
• C oss-Pla o m Resea ch: Compa e digi al lea ning pla o ms ac oss di e en academic
disciplines (enginee ing, social sciences, medicine, a s);
• Neu o-Me hodological UX S udies: Apply expe imen al me hods such as eye- acking,
EEG, and emo ion-based esponse analysis o e alua e use expe ience;
• Policy-Le el Applica ion: Explo e he po en ial in eg a ion o he p oposed model in o
Uzbekis an’s “Digi al Educa ion 2030” s a egic ini ia i es.
In conclusion, his s udy in oduces a no el app oach ha b idges heo e ical ounda ions
and p ac ical solu ions in e alua ing pe sonalized highe educa ion sys ems. Fu u e esea ch will
con inue along his ajec o y by in eg a ing digi al educa ion policies wi h inno a i e echnologies
o s eng hen adap i e and da a-d i en lea ning ecosys ems.
REFERENCES
THE VI INTERNATIONAL SCIENTIFIC CONFERENCE “SCIENTIFIC FOUNDATIONS FOR THE USE OF
INFORMATION TECHNOLOGIES OF A NEW LEVEL AND MODERN PROBLEMS OF AUTOMATION”,
NOVEMBER 20, 2025
208
1. Me ino-Campos, C. (2025). The Impac o A i icial In elligence on Pe sonalized Lea ning in
Highe Educa ion: A Sys ema ic Re iew. T ends in Highe Educa ion, 4(2), 17.
2. Saleem, S., Aziz, M. U., Iqbal, M. J., & Abbas, S. (2025). AI in Educa ion: Pe sonalized
Lea ning Sys ems and Thei Impac on S uden Pe o mance and Engagemen . C i ical
Re iew o Social Sciences S udies, 3(1), 2445–2459.
3. Yaseen, H. (2025). The Mode a ing Role o Digi al Li e acy. Sus ainabili y, 17(3), 1133.
4. S ielkowski, W. (2025). AI-D i en Adap i e Lea ning o Sus ainable Educa ional
De elopmen . Sus ainable De elopmen Jou nal.
5. Shi, P., e al. (2025). Adap i e Lea ning O ien ed Highe Educa ional Class oom: New
Teaching Plans h ough Deep Lea ning Me hods. Scien i ic Repo s.
6. Ha is, H. (2024). Facul y Pe spec i es Towa d A i icial In elligence in Highe Educa ion.
Doc o al disse a ion, Middle Geo gia Uni e si y.
7. Bel on, V., & S ewa , T. J. (2002). Mul iple c i e ia decision analysis: An in eg a ed app oach.
Sp inge Science & Business Media. h ps://doi.o g/10.1007/978-1-4615-1495-4
8. G eco, S., Ishizaka, A., Tasiou, M., & To isi, G. (2019). On he me hodological amewo k
o composi e indices: A e iew o he issues o weigh ing, agg ega ion, and obus ness. Social
Indica o s Resea ch, 141(1), 61–94. h ps://doi.o g/10.1007/s11205-017-1832-9
9. Ishizaka, A., & Neme y, P. (2013). Mul i-c i e ia decision analysis: Me hods and so wa e.
John Wiley & Sons. h ps://doi.o g/10.1002/9781118644898
10. O ganisa ion o Economic Co-ope a ion and De elopmen (OECD). (2008). Handbook on
cons uc ing composi e indica o s: Me hodology and use guide. OECD Publishing.
h ps://doi.o g/10.1787/9789264043466-en.
