Data Mining
Implementation to
Predict Sales using
Time Series Method
2
Guided BY
Md. Shahiduzzaman
Assistant Professor,
Department Of CSE(BUBT)
Group Member
Raihan Sikdar
ID-17181103133
Md Momin
ID-17181103046
Table of contents
⬥ Introduction
⬥ Objective
⬥ Research Method
⬥ Research Flowchart
⬥ What is Data Mining?
⬥ Data Mining Process Flowchart
⬥ Implementation and Application Testing
⬥ Graph of transaction and Forecast
⬥ Conclusion
⬥ References
3
⬥ Introduction
4
⬥ Transaction is the core activity from a business process and a
cycle that consistently done in several period of time.
Transaction started from the very beginning of a business
process began its activity.
⬥ Objective
5
⬥ A time series is a data set that tracks a sample over time. In
particular, a time series allows one to see what factors
influence certain variables from period to period. Time series
analysis can be useful to see how a given asset, security, or
economic variable changes over time.
RESEARCH METHOD
6
Forecasting
Evaluation
Data Mining
Data source Research
Dataset and Application
Forecasting Time Series
Moving Average
Data resource for this research
comes from sales transaction of a
company that sells its product
through distributors in Indonesia.
The data taken from January 2015
until December 2018 with range
around 5,000 data per year.
Ft+1 : forecast value for the time
period to t+1
Xt : actual value for t period
n : amount of data
7
Data Collection
Construct moving
average model
and forecasting
evolution
Forecasting the
data and evaluate
Analyses the
result
Develop the
dataset and
application
Determine the
forecasting
model
Start
End
Research
flowchart.
What is Data Mining?
1 Data mining is the exploration and analysis of data in order to
uncover patterns or rules that are meaningful. It is classified
as a discipline within the field of data science. Data mining
techniques are to make machine learning (ML) models that
enable artificial intelligence (AI) applications. An example of
data mining within artificial intelligence includes things like
search engine algorithms and recommendation systems
Flowchart of Data Mining
Process
2
10
Dataset Clustering
Classification
Prediction
Association
Clustered
?
Classified
?
Strat
End
NO
Yes
No
Yes
Implementation and Application Testing
11
Clustering Classification
Prediction Association
Graph of transaction and Forecast
12
⬥ CONCLUSION
13
⬥ Forecasting is almost impossible to produce data accuracy of
100%. In this case, the highest forecasting value with the
calculation of MAPE is 99.68%, namely in December. The lowest
yield forecasting occurred in May with forecasting accuracy still
above 50%. Even so, forecasting can still be used to bring up
numerical estimates that can be used in business processes
assisted by the patterns formed on the graph.
THANKS!
ANY QUESTIONS?
14
 S. Kamble, A. Desai, and P. Vartak, “Data Mining and Data
Warehousing for Supply Chain Management”, ICCICT, 2015
IEEE: 978-1-4799-5522-0/15/$31.00,Thakur Collage of
Engineering, Mumbai, India, 2015.
 W. Huang, Q. Xiao, H. Dai and N. Yan, "Sales Forecast for O2O
Services - Based on Incremental Random Forest Method,"
2018 15th International Conference on Service Systems and
Service Management (ICSSSM), Hangzhou, pp. 1-5, 2018.
 Y. Kaneko, "Customer-Base Sequential Data Analysis: An
Application of Attentive Neural Networks to Sales
REFERENCES
15
 S. Cheriyan, S. Ibrahim, S. Mohanan and S. Treesa, "Intelligent Sales
Prediction Using Machine Learning Techniques," 2018 International
Conference on Computing, Electronics & Communications
Engineering (iCCECE), Southend, United Kingdom, pp. 53-58, 2018
 X. Xu, L. Tang and V. Rangan, "Hitting your number or not? A robust
& intelligent sales forecast system," 2017 IEEE International
Conference on Big Data (Big Data), Boston, MA, pp. 3613-3622, 2017.
 P. Sobreiro, D. Martinho and A. Pratas, "Sales forecast in an IT company
using time series," 2018 13th Iberian Conference on Information Systems and
Technologies (CISTI), Caceres, pp. 1-5, 2018.
 T. Silwattananusarn, and Assoc. Prof. Dr. K. Tuamsuk, “Data Mining and its
Applications for Knowledge Management: A Literature Review from 2007 to
2012”, International Journal of Data Mining & Knowledge Management
Process, Vol. 2, No. 5, September, 2018.
16

Data mining-implementation-to-predict-sales-using-time-series-method By Raihan Sikdar

  • 1.
    Data Mining Implementation to PredictSales using Time Series Method
  • 2.
    2 Guided BY Md. Shahiduzzaman AssistantProfessor, Department Of CSE(BUBT) Group Member Raihan Sikdar ID-17181103133 Md Momin ID-17181103046
  • 3.
    Table of contents ⬥Introduction ⬥ Objective ⬥ Research Method ⬥ Research Flowchart ⬥ What is Data Mining? ⬥ Data Mining Process Flowchart ⬥ Implementation and Application Testing ⬥ Graph of transaction and Forecast ⬥ Conclusion ⬥ References 3
  • 4.
    ⬥ Introduction 4 ⬥ Transactionis the core activity from a business process and a cycle that consistently done in several period of time. Transaction started from the very beginning of a business process began its activity.
  • 5.
    ⬥ Objective 5 ⬥ Atime series is a data set that tracks a sample over time. In particular, a time series allows one to see what factors influence certain variables from period to period. Time series analysis can be useful to see how a given asset, security, or economic variable changes over time.
  • 6.
    RESEARCH METHOD 6 Forecasting Evaluation Data Mining Datasource Research Dataset and Application Forecasting Time Series Moving Average Data resource for this research comes from sales transaction of a company that sells its product through distributors in Indonesia. The data taken from January 2015 until December 2018 with range around 5,000 data per year. Ft+1 : forecast value for the time period to t+1 Xt : actual value for t period n : amount of data
  • 7.
    7 Data Collection Construct moving averagemodel and forecasting evolution Forecasting the data and evaluate Analyses the result Develop the dataset and application Determine the forecasting model Start End Research flowchart.
  • 8.
    What is DataMining? 1 Data mining is the exploration and analysis of data in order to uncover patterns or rules that are meaningful. It is classified as a discipline within the field of data science. Data mining techniques are to make machine learning (ML) models that enable artificial intelligence (AI) applications. An example of data mining within artificial intelligence includes things like search engine algorithms and recommendation systems
  • 9.
    Flowchart of DataMining Process 2
  • 10.
  • 11.
    Implementation and ApplicationTesting 11 Clustering Classification Prediction Association
  • 12.
    Graph of transactionand Forecast 12
  • 13.
    ⬥ CONCLUSION 13 ⬥ Forecastingis almost impossible to produce data accuracy of 100%. In this case, the highest forecasting value with the calculation of MAPE is 99.68%, namely in December. The lowest yield forecasting occurred in May with forecasting accuracy still above 50%. Even so, forecasting can still be used to bring up numerical estimates that can be used in business processes assisted by the patterns formed on the graph.
  • 14.
  • 15.
     S. Kamble,A. Desai, and P. Vartak, “Data Mining and Data Warehousing for Supply Chain Management”, ICCICT, 2015 IEEE: 978-1-4799-5522-0/15/$31.00,Thakur Collage of Engineering, Mumbai, India, 2015.  W. Huang, Q. Xiao, H. Dai and N. Yan, "Sales Forecast for O2O Services - Based on Incremental Random Forest Method," 2018 15th International Conference on Service Systems and Service Management (ICSSSM), Hangzhou, pp. 1-5, 2018.  Y. Kaneko, "Customer-Base Sequential Data Analysis: An Application of Attentive Neural Networks to Sales REFERENCES 15
  • 16.
     S. Cheriyan,S. Ibrahim, S. Mohanan and S. Treesa, "Intelligent Sales Prediction Using Machine Learning Techniques," 2018 International Conference on Computing, Electronics & Communications Engineering (iCCECE), Southend, United Kingdom, pp. 53-58, 2018  X. Xu, L. Tang and V. Rangan, "Hitting your number or not? A robust & intelligent sales forecast system," 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, pp. 3613-3622, 2017.  P. Sobreiro, D. Martinho and A. Pratas, "Sales forecast in an IT company using time series," 2018 13th Iberian Conference on Information Systems and Technologies (CISTI), Caceres, pp. 1-5, 2018.  T. Silwattananusarn, and Assoc. Prof. Dr. K. Tuamsuk, “Data Mining and its Applications for Knowledge Management: A Literature Review from 2007 to 2012”, International Journal of Data Mining & Knowledge Management Process, Vol. 2, No. 5, September, 2018. 16