Research Journal

Online ISSN No. 2790 – 3885

Effects of Predictive Data Analytics
Using Big Data Analytics on Inventory
Optimization in Landmark Group

Nilesh Mohan Kamble
ORCID No: 0000-0001-8669-6413
Email: nilesh64472@gmail.com
Westford University College – UCAM Spain
Ms Anjali Tewari
ORCID No. 0000-0002-7662-8166
Email : anjalitmamgain@gmail.com


The present study attempted to examine the influence of predictive data analytics using big data analysis on
the performance of inventory optimisation enablers in the Landmark Group, UAE. Landmark Group, UAE
has invested heavily in Industry 4.0 technologies in the recent past and has implemented predictive analytics
capability. Considering the organisation as valid research setting for investigating the topic, a survey was
conducted using a structured questionnaire designed in accordance with an initial theoretical construct,
which in turn was designed with the help of detailed review of literature. The initial theoretical construct was
designed with usage of predictive data analytics techniques as independent variables and inventory
optimisation enablers as dependent variables. The data collected was encoded and analysed through
descriptive statistical analysis and multivariate analysis of variance, which were selected as methods under
the positivism paradigm with deductive learning and quantitative methodology. The analysis was done
without and with big data characteristics applied as moderators. The results showed significant influence of
Support Vector Machine and Flow-based Events Analysis on the inventory optimisation enablers even with
limited usage. Other influential techniques found were Demands Pattern Recognition, Demand – Supply
Predictions, and Regression Analysis. However, significant negative effects of big data characteristics were discovered as moderators. This finding reflected the risks of overloading predictive data analytics techniques
with big data without appropriate processing following the methods of categorisation, contextual
classification, data cleaning, and data quality auditing before using them for predictive analytics.

Keywords— Demands Pattern Recognition, Demand – Supply Predictions, Support Vector Machine,
Flow-based Events Analysis, and inventory optimisation.