Big Data Analytics for Preschool

Mohamed Bellaj

, Abdelaziz El Hibaoui

and Ahmed Bendahmane

Computer Science and Systems Engineering Laboratory, ABDELMALEK ESSAADI University, Faculty of Science, Tetuan,

Morocco

Applied Sciences and Education Laboratory, ABDELMALEK ESSAADI University, Higher Normal School, Tetuan,

Morocco

Keywords: Big Data, Preschool, Education; Analytics

Abstract: This paper offers a detailed examination of Big Data Analytics (BDT) benefits, processes, and challenges in

the preschool education sector. By simplifying institutions, organizations, instructor techniques, statistical

instruction, and evaluation processes BDT plays an essential role in maximizing education intelligence.

Furthermore, BDT was used to examine, classify, and forecast learners' needs, as well as vulnerability

shortcomings and results, to advance their awareness outcomes and ensure that instructional programs are of

high quality. The phases of jobs Big Data and how to process it were also described in this paper. While BDT

makes a significant contribution to education, it faces several challenges in terms of security, privacy, ethics,

and a shortage of qualified personnel, as well as data processing and storage. As a result, we will discuss the

causes of some of the problems associated with applying big data analytics in the preschool market, as well

as some recommendations for overcoming those challenges.

1 INTRODUCTION

In the educational sphere, professors’ entire

pedagogical decisions to assess a student's

comprehension of the content or plan the layout of a

course can have the most significant impact on

student learning and graduation. High-grade

lessons can shorten the time it takes a student to learn

a particular subject, allow students to obtain more

knowledge in the same amount of time, and assist

them in making effective choices about what they can

specifically learn and drill.

This learning productivity not only improves the

student's capacity but also saves time. However, it

also benefits teachers by reducing some of their

demands. Big Data Analytics is the most practical

method for enabling the flexible decision-making that

educators need to improve the consistency of the

educational environment. It is a cost-effective way to

give educators and apprentices an advantage in

determining when and how improvements should be



https://orcid.org/0000-0002-7057-6107

https://orcid.org/0000-0003-2167-0831

https://orcid.org/0000-0003-3843-4800



made in the learning process (A. Franco, Pablo

Daniel, Antonio Matas, and Juan José Leiva. 2020).

A series of decisions, most lauded in the area of

product innovation, has been made to modernize the

education sector industry. Big Data Analytics opens

up new possibilities for advancing the educational

process. Assist teachers and students in making more

informed choices early in the learning process

(Reidenberg, Joel R., and Florian Schaub. 2018).

Data science is being used to accelerate practice

creativity, and progress is being made quickly. Nearly

every day, new technologies and intelligent

applications are developed to assist students and

educators in making better use of their time.

Technology has always been and will continue to

be an important part of our work. Even, the most

important thing is how we, as educators, use the

influence of digital technologies to help our

decisions. What is commonly called “soft skills”;

provides teachers with the ability to develop cognitive

and emotional intelligence.

Bellaj, M., El Hibaoui, A. and Bendahmane, A.

Big Data Analytics for Preschool.

DOI: 10.5220/0010736500003101

In Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning (BML 2021), pages 457-465

ISBN: 978-989-758-559-3

457

Educators and students must understand how data

analytics can improve the learning experience to

create the correct interrogations and to mark the

preeminent use of big data as a device to advance our

decision-making.

Most states do not systematically collect

information on how early childhood education

programs collect and use data. Given this lack of

information, the results from the current study help

provide the early childhood community with detail on

data collection and use in early childhood education

classrooms (Zweig Clare W. Irwin Janna Fuccillo

Kook Josh Cox .2015).

2 BIG DATA AND EDUCATION

Big Data, in its proper sense, refers to the massive

amount of data that floats over several stations and,

more broadly, digitally in any fleeting moment. It's

data that's too large, complex, and volatile for

traditional tools to release and handle. The format

emerged in the free public domain, where experts

were attempting to find faster and more usable ways

to collect and process massive amounts of data. This

data can now be explored and viewed as benefits to

technological advancements, bringing limitless

advantages to the government, education,

engineering, healthcare, and other data-driven

practices.

To be familiar with the concept of having Large

Data “big” defining by both in dimension and

meaning, particularly in education, allows for the

exploration and prediction of learners behaviour

across an enormous variety of contexts, acquisition

degree, personal backgrounds, reflective progressions,

academic intentions, environmental characteristics,

personal potentials, skills –eve (Naga, I. and Hao, Y.

2014; Nessi. 2012).

The majority of these data considerations are

currently being investigated in the education field to

help devise instructional methods, analyze and

measure the impact of these approaches on both

learners and educators, and in general, all of which

will help create a transformation in the educational

sector by developing an effective learning

environment.

3 PRESCHOOL EDUCATION

ANALYTICS

In preschool, pupils are the main body of learning.

Both teaching activities should be carried out to

promote children's progress. A children-centered

curriculum focuses on transforming passive

education in children into constructive knowledge

through the education process.

The unpredictability of learning activities puts

forward high requirements for teachers. Big data

analytics can offer a vast number of learning

opportunities to all pupils, learning experiences can

be designed in real-time based on the children's

reactions to the learning activities (Ling Jin,2019).

When the number of states that have publicly

subsidized preschool education increases, states are

developing monitoring mechanisms to help assess

program success and, as a result, how efficiently the

public's money is used (By Shannon Riley-Ayers,

Ellen Frede, W. Steven Barnett, and Kimberly

Brenneman,2011).

In reality, the majority of state assessments of

preschool systems are less than comprehensive in

terms of science criteria, with many possessing such

defects that understanding their findings is severely

limited (Gilliam, W. S. & Zigler, E. F. 2000)

(Gilliam, W. S. & Zigler, E. F. 2004).

Early childhood education systems are under -

demand to gather data on both teachers and students

and to use the data to make decisions.

Two significant impediments can prohibit early

childhood educators from effectively using data to

guide decisions. The first is a scarcity of literature on

the best methods for data use in early childhood

education. The second issue is a lack of capacity

among preschool systems to collect data and use the

findings to make decisions (Yazejian, N., & Bryant,

D. 2013).

4 BIG DATA DIMENSIONS

In one view, Doug Laney (Doug Laney, 2011)

describes Big Data as having three dimensions:

volume, variety, and velocity. Thus, International

Data Corporation (IDC) defined it: “Big data

technologies refer to a new wave of technologies and

architectures that allow high-velocity data collection,

exploration, and, or analysis to economically extract

value from enormous quantities of a wide variety of

data.” Two more characteristics seem to be

BML 2021 - INTERNATIONAL CONFERENCE ON BIG DATA, MODELLING AND MACHINE LEARNING (BML’21)

458

significant: value and complexity. In the following

paragraph, we will outline these characteristics.

Three Vs

Many examples of big data concentrate on the amount

of data in storage, and size does matter, there are other

essential characteristics of big data, such as data

variety and velocity. The three Vs of big data

(volume, variety, and velocity) (K. U. Jaseena and J.

M. David,2014) constitute a thorough overview and

dispel the misconception that big data is solely about

data volume. In addition, each of the three Vs has its

implications for analytics (See Figure 1).

Big data is everywhere over us, even though we

don't recognize it right away. Part of the issue is that,

even under exceptional circumstances, the rest of us

do not agree with vast quantities of data in our

everyday lives. We frequently struggle to grasp both

the possibilities and threats posed by big data because

we lack this immediate knowledge. As a result of

these characteristics, there are currently many

disagreements and difficulties in overcoming these

characteristics in the future.

 Data Volume: That means

 it assesses the

amount of data accessible to an organization and

does not have to own any of it as long as it has

access to it. The importance of diverse data

records will decline as data volume grows

concerning age, richness, form, and quantity,

among other factors(A. TOLE,2013) (D.

Laney,2001).

 Data Velocity: Data velocity refers to how

quickly data is created, streamed, and

aggregated. The speed and richness of data used

by a variety of private transactions have steadily

increased(for example, website clicks). Data

velocity control is more than just a bandwidth

problem; it's also an issue with data that's been

swallowed (extract-transform-load) (K. S. Dr

Jangala., M. Sravanthi, K. Preethi and M.

Anusha,2015).

 Data Variety: Data variety is a measure of the

richness of the information representation – text,

images video, audio, etc. From an analytic

perspective, it is possibly the principal obstacle

to effectively using large volumes of data.

Non-structured data, incompatible data

arrangements, and ambiguous data semantics all

pose major obstacles to analytic expansion (K. U.

Jaseena and J. M. David,2014).

 Data Value: This stage assesses the usefulness

of data in decision-making (K. U. Jaseena and J.

M. David,2014). It has been noted that “the

purpose

of computing is insight, not numbers”.

Figure 1: Three Vs of Big Data

Data science is the study of and applying data to

recognize it, but “analytic science” involvesthe

statistical monitoring of large amounts of data.

 Complexity: The degree of interconnectedness

is measured by complexity (probably very

immense) and interdependence in large data

structures such that a slight modification (or

arrangement of small changes). Rather big

changes or a minor transition that ripple through

the system and significantly marks its behaviour,

or no change at all, can be achieved by changing

one or a few elements (Katal, A., Wazid, M., &

Goudar, R. H. 2013).



5 BENEFITS OF BIG DATA

IMPLEMENTATION IN

PRESCHOOL

We will gain a thorough understanding of the

educational process and its mechanism by using Big

Data's different methods of data analysis.

The following are some of the most popular uses for

Big Data in the preschool sector:

Collaboration:Many experts from various fields and

backgrounds may share their knowledge and establish

collaborative centres. These programs improve

educational methods by encouraging teamwork and

coordination, as well as coordinating academic views

(Zweig, J., Irwin, C. W., Kook, J. F., & Cox, J. 2015).

Understanding the learning process: Any features,

patterns, and learning speeds are unique to each

learner. We will derive various recommendations to

improve the learning process by providing insight

into the educational learner's direction.

Feedback: The failure to recognize the causes of the

issue and how to solve it is one of the most common

challenges that the school system faces. We may

Big Data Analytics for Preschool

459

immediately determine the reason for a learner's

failure using the conventional approach, but the

learner can fail again.To address the issue, modern

techniques propose extracting previously collected

data from each learner's route and offering alternate

methods of correction (Franco, Pablo Daniel, Antonio

Matas, and Juan José Leiva,2020).

Predicting: Based on their profiles, specialists may

create a viable curriculum performance for the next

generation, using digital traces preserved from past

interactions with the platform, as well as other

evidence (Burchinal, M. R., Kainz, K., & Cai, Y.

2011).

Motivation: after seeing the implications of

extensive data adoption, learners can see the gain and

become more persuaded that they can see the impact

of how this happens (Theodotou, E. 2014).

6 EDUCATIONAL BIG DATA

NEEDS, OPPORTUNITIES, AND

CHALLENGES

Figure 2: Educational Big Data Needs, Opportunities and

Challenges adapted from (Shikha Anirban,2014)

For educators, big data analytics is now posing a

significant challenge. People are currently concerned

about institutions' intelligent outcomes of learning

about pupils' learning and research institutions' blind

pursuit of big data analytics without understanding

the ramifications (Shikha Anirban,2014).

Figure 2 represents the educational (learning and

academic) analytics from three aspects: Needs,

Opportunities, and Challenges.

7 BIG DATA PROCESS AND

CHALLENGES IN EDUCATION

7.1 Collection: Challenges and

Propositions

The first step in revealing the importance of Big Data

is to gather data. This necessitates the identification

of data that may reveal useful and important

knowledge. Data must be filtered for relevance and

stored in a usable format since there is no point in

spending money on massive amounts of data and

computing infrastructure if the vast majority of the

data in it is useless.

There are also difficulties with the accuracy of the

data that has been gathered and described. Since the

quality of data obtained by Big Data is entirely

dependent on the quality of data gathered and the

robustness of the procedures or metrics used, inter

(national) comparison and assessment is complicated.

challenges

1. Ethics: Identifying the institute methods for

protecting personal learner data protection,

human approval, data ownership, and

accountability are among the ethical issues for

Big Data Analytics in Preschool. These issues

exist when educational data collection and use

are not subject to any formal ethics review.

Moreover, difficulties arise when the data

sources are complex and sophisticated (Willis,

J.; Campbell, J.; and Pistilli, M. 2013)(

Royal

Statistical Society 2015).

2. Heterogeneity: The heterogeneity of data

sources is the most important issue in the data

collection process. (Jagadish, H. V., Gehrke, J.,

Labrinidis, A., Papakonstantinou, Y., Patel, J.

M., Ramakrishnan, R., & Shahabi, C. 2014)

Because of the diversity, representation, and

semantics of the data sources, heterogeneous

data complications rise. Furthermore, the

majority of the new data generated is

fundamentally different from the data forms on

which the original structures were developed.

Date formats and character fields are the most

prevalent sources of representational errors.

Database creators may attempt to link datasets

using the student's name and surname to extract

some vital information. Since character fields

BML 2021 - INTERNATIONAL CONFERENCE ON BIG DATA, MODELLING AND MACHINE LEARNING (BML’21)

460

Figure 3: Big data process and challenges tree in education by authors

are item sensitive, even minor

misrepresentation, such as using different

capital letters, can slow down joins and

searches.

3. Size of data: Another major issue is

transferring the captured data. The speed at

which the data is transferred could be a

bottleneck in the process due to the size of the

data (Jagadish, H. V., Gehrke, J., Labrinidis,

A., Papakonstantinou, Y., Patel, J. M.,

Ramakrishnan, R., & Shahabi, C. 2014).

4. Energy and resources: Storing and loading

such a large amount of data necessitates a

significant amount of energy and money.

Finding the best-located servers to store the data

is one of the challenges of Big Data. In addition,

the server sites must be energy-efficient and

flexible. The location is essential due to the

speed of transfer of the stored data to do the

analyses.

5. Encryption: Many secure transmissions

necessitate some kind of encryption that must

be agreed upon in advance by scholar

institutions and learners' parents; however,

institutions do not create commons laws to

justify such measures and

procedures(B.Tulasi,2013)

6. Data security: The unregulated accumulation

of data by various organizations is perhaps the

most severe threat to personal security (game

application, social media…). This information

raises serious security concerns, particularly

because too many people voluntarily hand over

that information (Luo Ying,2016). There are

also questions about data fidelity and accuracy,

as well as distribution, expiration, and access.

 Propositions

i. Several big data educational programs must be

safeguarded in terms of privacy and security laws

and procedures. IDC suggested five levels of

increasing security: Privacy, compliance-driven,

custodial, sensitive, and lockout are all words that

come to mind when thinking about data security.

Further research is needed to clearly identify these

protection levels and compare them to existing law

and analytics.

ii.For these reasons, ethical standards are required to

ensure that data stewardship and ownership are

established, and privacy concerns are addressed,

ensuring that data is shielded from misuse.

Educators and organizations will help educate

curriculum design and pedagogy in this way, thus

allowing students to become more aware of their

learning habits.

iii. Data users and developers must be mindful that

data must be changed and modified regularly to be

used effectively.

iv.Since storing large amounts of data can be costly,

some organizations have attempted to retain only

a portion of the data gathered. As a result,

interpreting data extraction findings may be more

difficult; on the other hand, a portion of false

connections and unexplained data ties can occur.

Big Data Analytics for Preschool

461

v. If the information is used for the benefit of the

learners, such as predicting student actions and

presenting a series of recommendations and

services based on Learning Analytics, or if it is

used for research to satisfy Learning Analytics

intentions, the searchers must clarify how the

information is used. Also, define the time frame

during which learners' data is held, as well as a

deletion procedure.

7.2 Analysis: Challenges and

Propositions

Once data has been transformed into a usable format,

it must be processed to generate actionable

information. However, as the quality of information

becomes more diverse, handling and interpreting a

diverse data set is becoming more complex. To

understand the information that is meant to be

transported by these data, the analysis must involve

referencing, integrating, and correlating disparate

data sets.

As a result, the complexity of Big Data has been

coined. But, how can we ensure that all data of a

particular nature is precise and reliable? Or, to put it

another way, incorrect results aren't the only issue

with big data analytics. The speed at which the tests

are completed is the main issue. This is one of the big

data's three V's. Volume, Variety, and Velocity are

the most common definitions for these Vs.

 challenges

a. Variety and Volume: During the data

collection and incorporation process, the terms

"volume" and "variety" were discussed.

b. Velocity: Large data velocities not only do it

refer to the flow of data from sources to

databases, but also refers to the flow of

information from databases to the final

analytics result. The speed at which data is

extracted and analyzed is the most significant

competitive advantage that an enterprise can

achieve.

c. Infrastructure faults: Huge amounts of data

that are critical to a company's success must be

stored and analyzed, which necessitates a large

and complex hardware system. More hardware

structures would be needed as more and more

complex data is processed. A hardware device

can only be trusted for a limited amount of

time. Intensive use and, in rare circumstances,

production flaws would almost inevitably

trigger a machine failure (Bala M.

Balachandran, and Shivika Prasad,2017).

d. Software problems: Data loss isn't necessarily

a hardware problem. Software may even fail,

resulting in irreversible and potentially unsafe

data loss. When a hard disk fails, there is

usually another one to back it up, so data is not

destroyed; but, when the software fails due to

a programming "bug" or a design mistake,

information is lost permanently. Hardware

features restrict software solutions

(CTI,10,2018).

 Propositions

i.Correct and timely decisions would maximize the

return on investment and the institutions'

educational-solution share. However, to examine

the dynamic development of big data in

education, a long-term financial plan is needed.

ii.To prevent such disasters, they use a backup

mechanism that performs the primary task of

saving all records. Companies gain continuity as

a result of this, even though they are temporarily

retracted.

iii.To address this problem, programmers devised a

set of tools that would mitigate the consequences

of a technological malfunction. Microsoft Word,

for example, periodically saves the work that a

user is performing to avoid data loss in the event

of hardware or software failure. This is the

fundamental concept behind avoiding total data

loss.

7.3 Visualization: Challenges and

Propositions

This is the final point, in which the evaluated data is

made available to users in an interpretable format that

can be implemented into existing systems and then

used to direct decision-making.

We can resume the data visualization process by

several steps noted below:

Prediction: Learner habits and potential success can

be revealed by anticipation. As a result, appropriate

action will help Learning Analytics achieve its

objectives.

Intervention: Identify scholars who may be at risk,

provide advice to learners who may need extra

support, and help students succeed.

Recommendation: The ability to make

recommendations to learners based on their activities

is the primary objective of Learning Analytics.

Personalization: accelerate academic creativity and

increase educational results. it can be done, for

example, by personalizing e-learning based on a

BML 2021 - INTERNATIONAL CONFERENCE ON BIG DATA, MODELLING AND MACHINE LEARNING (BML’21)

462

learner's skill or by assisting students with

personalized learning tips.

Reflection and Iteration: Reflection aims to analyze

previous work to enhance future experiences and to

transform it into learning through personalization and

adaptation. This iteration will maximize all Learning

Analytics stakeholders in the design of its loop.

Benchmarking: Benchmarking is a method of

learning that recognizes the best practices that yield

superior outcomes. These activities are being repeated

to improve success outcomes (Vorhies DW, Morgan

NA. 2005).



challenges

a. It is important to understand the degree of

exactness that the handler needs to identify

adequate data to produce an estimation or forecast

of the specific likelihood and precision of a given

outcome.

b. Determine what amount of time evidence is still

operational and whether the relevance of publicly

available findings expires.

c. To protect learner privacy, Big Data in Education

requires disclosure, which makes the identity of

the student available to disclose decisions.

Furthermore, using Big Data Analytics

implementations to forecast learners' potential

educational results, realistic efficiency, and

engagement could jeopardize their privacy.

d. Because of the strong connection, the prototype's

removed details may have become improper

statistical ones that exposed the erroneous

correlation and misleading linkage to the

specified component.

e. Big data poses challenges for data scientists and

managers at any stage of the analytical process.

Institutions face greater problems in hiring

qualified data scientists who can work

professionally with big data than in the analytical

process itself (Daniel, B. 2014) (NARST 2015).

 Propositions

i. Create appropriate structures to efficiently

manage the results.

ii. The establishment of a common standard based

on internationally agreed-upon fundamental

values would be a huge advantage as well.

These revisions should include important

existing considerations, circumstances, and

complexities, as well as the development of

specific protocols and the provision of

acceptable conversion times for implementing

the necessary modifications.

iii. States, especially high-tech firms, must have

more financial capital to stimulate investment in

this domain and to simplify laws by creating

less complicated procedures.

iv. Sensitize parents and educators by assisting

organizations in manipulating their knowledge

and outcomes, as they play an important role in

facilitating the first step for scientists

v. Institutions all over the world must reduce the

number of methods and techniques used in the

educational arena and work together to develop

international rules that can standardize the

complex data process and increase the efficacy

of the outcomes.

Common challenges: Build a specialized centre

over the world to overcome the lack of Big Data

researchers in education, and promote the

competence of the staff during each process of

treatment.

8 CONCLUSION

While we can establish and incorporate effective

solutions to address learning barriers from preschool

to high school by concentrating efforts on the child

learning process, we discovered a lack of studies that

shed light on big data analytics in preschool (BDTP)

problems process including their challenges.

This paper kicks off a joint exploration campaign

to look at (BDTP) questions and problems. Several

significant problems in big data collection,

administration, and implementation have been

identified. That is something we think needs to be

tackled over the next decade. Our upcoming study

will concentrate on gaining a skilled understanding of

the problems associated with (BDTP). Via our

research, we will continue to investigate more

effective solutions to some of the issues posed in this

article.

Big Data Analytics for Preschool

463

Table 1: Summarizing the Grid of big data analytics challenges and propositions by authors

REFERENCES

A. Franco, Pablo Daniel, Antonio Matas, and Juan José

Leiva. 2020. " Big Data irruption in education". Pixel-

Bit. Revista de Medios y Educación 57: 59–90.

Reidenberg, Joel R., and Florian Schaub. 2018. "Achieving

big data privacy in education". Theory and Research in

Education 16: 263–79

Zweig Clare W. Irwin Janna Fuccillo Kook Josh Cox,

"Data collection and use in early childhood education

programs": Evidence from the Northeast Region

Jacqueline Education Development Center, Inc. In

collaboration with the Early Childhood Education

Research Alliance

Naga, I. and Hao, Y. (2014). " A Holistic Analysis of Cloud-

Based Big Data Mining". International Journal of

Knowledge, Innovation, and Entrepreneurship. Volume

2 No. 2, 2014, pp. 56—64. Retrieved from:

http://ijkie.org/IJKIE_December2014_IRINA&HAO.p

NESSI. (2012). Big Data: A New World of Opportunities.

Retrieved from:http://www.nessi-europe.com

/Files/Private/NESSI_WhitePaper_BigData.pdf.

Ling Jin, "Investigation on Potential Application of

Artificial Intelligence in Preschool Children’s

Education", To cite this article: 2019 J. Phys.: Conf.

Ser. 1288 012072

By Shannon Riley-Ayers, Ellen Frede, W. Steven Barnett,

and Kimberly Brenneman, "Improving

Early Education Programs through Data-based Decision

Makin" (2011).

Gilliam, W. S. & Zigler, E. F. (2000). A critical meta-

analysis of all evaluations of state-funded preschool

from 1977-1998: Implications for policy, service

delivery, and program evaluation. Early Childhood

Research Quarterly, 15(4), 441-473.

Gilliam, W. S. & Zigler, E. F. (2004). "State efforts to

evaluate the effects of prekindergarten": 1977-2003.

Retrieved September 10, 2008.

Yazejian, N., & Bryant, D. (2013). Embedded,

collaborative, comprehensive: One model of data

utilization. Early Education and Development, 24(1),

68–70.

Doug Laney "Pattern-Based Strategy: Getting Value from

Big Data.," Gartner Group press release. . Available at

http://www.gartner.com/it/page.jsp?id=1731916, July

2011

Process of Big data Analytics in preschool with some propositions

Process

issues

Challenge propositions Comments

(

)

: stron

ness

(

)

: weakness

collection Ethics enabling the pupil to become further conscious of

their own learning behaviors

(+) give learners a self-confident and protect

their rights

(-) require collaboration

Heterogeneity Establish a periodic revise of DATA stored (+) simple to update

(-) application require a periodic

modification

Size of data

Storing a part of the data collected (+) resolve a part of whole problems

(

)

losin

some sensible information

Energy and

resources:

Looking for an approximate location to minimize

distance between stations

(+) accelerate the process of data acquisition

(-) very costly

Encryption:

Establish an efficient common encryption strategy (+) Has huge potential, can protect data

versus attackers

(

)

Has limitations outcomes

Data security

Increasing security levels and standardizes it (+) efficient mechanism to protect data

(-) more sustained efforts towards

lementation are re

uire

analytics Variety and

Volume

Follow and examine data process progression (+) very important to start any analytics

process

(

)

lack of indicators

recision

Velocity

Corporation between organization to plan the fast

decisions

(+) reach certified results

(

)

uire a cost resources

Infrastructure

faults

Develop a series of tools to reduce the impact of

hardware failure

(+) provide a useful mechanism to gain

additional time

(

)

insufficient bud

Software problem

use a backup system (+) reduce the rate of failure

(-) limited update

visualization level of precision

Design appropriate systems and minimize strategies

around the wor

(+) reach an operational results

(

)

less level of collaboration

Data expiration

Allow sufficient transition periods to apply the

convenient chan

(+) keep the suitable and useful data

(

)

Not feasible

the ma

orit

of institution

Privacy

Sensitize the parents and learners and demand their

ermission

(+) protect pupil’s confidentialities

(-) need collaboration

investment

provide more financial resources (+) the essential pillar for each changes

(

)

rare attractive results

Common challenge:wecanconsiderlackofskilledbigdataresearchersineducation.Themostsharedfactorbetweenalltheprocessesof

treatmentInbigdataanalytics.

BML 2021 - INTERNATIONAL CONFERENCE ON BIG DATA, MODELLING AND MACHINE LEARNING (BML’21)

464

K. U. Jaseena and J. M. David, "ISSUES, CHALLENGES,

AND SOLUTIONS: BIG DATA MINING," Computer

Science & Information Technology (CS & IT), no. pp.

131–140, 2014

A. TOLE, "Big Data Challenges," Database Systems

Journal, vol. Vol. IV, no. no. 3, pp. 31-40, 2013

D. Laney, "3D Data Management: Controlling Data

Volume, Velocity, and Variety," Stamford, February 6,

2001.

K. S. Dr. Jangala., M. Sravanthi, K. Preethi and M. Anusha,

"Recent Issues and Challenges on Big Data in Cloud

computing," IJCST, vol. Vol. 6, no. Issue 2, April - June

2015

K. U. Jaseena and J. M. David, "ISSUES, CHALLENGES,

AND SOLUTIONS: BIG DATA MINING," Computer

Science & Information Technology (CS & IT), no. pp.

131–140, 2014.

Katal, A., Wazid, M., & Goudar, R. H. (2013). "Big Data:

Issues, Challenges, Tools and Good Practices". IEEE,

404-409.

Zweig, J., Irwin, C. W., Kook, J. F., & Cox, J. (2015). "Data

collection and use in early childhood education

programs": Evidence from the Northeast Region (REL

2015–084). Washington, DC: U.S. Department of

Education, Institute of Education Sciences, National

Center for Education Evaluation and Regional

Assistance, Regional Educational Laboratory

Northeast & Islands. Retrieved from

http://ies.ed.gov/ncee/edlabs.

Franco, Pablo Daniel, Antonio Matas, and Juan José Leiva.

2020. Big Data irruption in education. Pixel-Bit.

Revista de Medios y Educación 57: 59–90

Burchinal, M. R., Kainz, K., & Cai, Y. (2011). How well

are our measures of quality predicting to child

outcomes: A meta-analysis and coordinated analyses of

data from large scale studies of early childhood

settings. In M. Zaslow, I. Martinez-Beck, K. Tout & T.

Halle (Eds.), Measuring quality in early childhood

settings (pp. 11–31). Baltimore: Brookes Publishing.

Theodotou, E. (2014). “Early Years Education: are Young

Students Intrinsically or Extrinsically Motivated

Towards School Activities? A Discussion about The

Effects of Rewards on Young Children’s Learning”.

Research in Teacher Education.Vol: 4 No:1 pp: 17–21.

Shikha Anirban, "Big Data Analytics in the Education

Sector: Needs,Opportunities and Challenges",

International Journal of Research in Computer and

Communication Technology, Vol 3, Issue 11, November

–2014

Willis, J.; Campbell, J.; and Pistilli, M. (2013). ethics, big

data, and analytics: an application model.

EDUCAUSE. Retrieved July 11, 2017, from

http://er.educause.edu/articles/2013/5/ethics-big-data-

and-analytics-a-model-for-application.

Royal Statistical Society (2015)."The opportunities and

ethics of big data. "report. Retrieved July 11, 2017,

from http://www.rss.org.uk/Images/PDF/ influencing-

change/2016/RSS-report-apps-and-ethics-of-big-data-

Feb-2016.pdf.).

Jagadish, H. V., Gehrke, J., Labrinidis, A.,

Papakonstantinou, Y., Patel, J. M., Ramakrishnan, R.,

& Shahabi, C. (2014). "Big data and its technical

challenges". Communications of the ACM, 57(7), 86–

94. doi:10.1145/2611567

B.Tulasi, "Significance of Big Data and Analytics in Higher

Education" , Journal of Computer Applications (0975 –

8887) Volume 68– No.14, April 2013 21.

Luo Ying. "Research on Big Data Security and Privacy

Protection (J). Information Communication",

2016(1):162-163.

Bala M. Balachandran, and Shivika Prasad, " Challenges

and Benefits of Deploying Big Data Analytics in the

Cloud for Business Intelligence", International

Conference on Knowledge-Based and Intelligent

Information and Engineering Systems, KES2017, 6-8

September 2017, Marseille, France.

CTI,10

Common Causes of Data Loss:

https://consoltech.com/blog/10-common-causes-of-

data-loss/

Vorhies DW, Morgan NA. 2005. Benchmarking marketing

capabilities for sustained competitive advantage.

Journal of Marketing 69(1): 80 – 94

Daniel, B. (2014). "Big data and analytics in higher

education: opportunities and challenges". British

Journal of Educational Technology, 46(5), 904-920.

NARST (2015). "Big data and learning analytics: a new

frontier in science and engineering education

research". Symposium presented at the annual meeting

of the National Association for Research in Science

Teaching. Chicago, IL 1-11, Retrieved June 6, 2017,

from: https://concord.org/sites/default/files/pdf/big-

data-and-learning-analytics.pdf.

Big Data Analytics for Preschool

465