Predictive analytics of chemical material pricing
Predictive analytics is the use of data, mathematical models and statistical algorithms to make predictions of the likelihood of future events. With the recent trend in technology and the ever-growing database of information, predictive analytics has become a catalyst to drive strategic decision mak...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/147902 |
| _version_ | 1826127760923295744 |
|---|---|
| author | Saini, Aditi |
| author2 | Zhang, Jie |
| author_facet | Zhang, Jie Saini, Aditi |
| author_sort | Saini, Aditi |
| collection | NTU |
| description | Predictive analytics is the use of data, mathematical models and statistical algorithms to make predictions of the likelihood of future events. With the recent trend in technology and the ever-growing database of information, predictive analytics has become a catalyst to drive strategic decision making in most businesses today.
This project explores the prediction of the prices of different raw material using time series- based analysis. Each raw material is composed of different chemicals, referred to as feedstocks. We investigate univariate and multivariate time series modelling techniques to create a generalised prediction pipeline using autocorrelation and cross-correlation analysis.
We show through experiments and with the help of metrics (i.e., Mean Absolute Error and Mean Absolute Prediction Error) that how a statistical machine learning model outperforms the existing rule-based prediction model by identifying the underlying trends through correlation and time lag analysis. |
| first_indexed | 2024-10-01T07:14:08Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/147902 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:14:08Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1479022021-04-16T06:06:40Z Predictive analytics of chemical material pricing Saini, Aditi Zhang, Jie School of Computer Science and Engineering Marcus De Carvalho ZhangJ@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Predictive analytics is the use of data, mathematical models and statistical algorithms to make predictions of the likelihood of future events. With the recent trend in technology and the ever-growing database of information, predictive analytics has become a catalyst to drive strategic decision making in most businesses today. This project explores the prediction of the prices of different raw material using time series- based analysis. Each raw material is composed of different chemicals, referred to as feedstocks. We investigate univariate and multivariate time series modelling techniques to create a generalised prediction pipeline using autocorrelation and cross-correlation analysis. We show through experiments and with the help of metrics (i.e., Mean Absolute Error and Mean Absolute Prediction Error) that how a statistical machine learning model outperforms the existing rule-based prediction model by identifying the underlying trends through correlation and time lag analysis. Bachelor of Engineering (Computer Science) 2021-04-16T06:06:40Z 2021-04-16T06:06:40Z 2021 Final Year Project (FYP) Saini, A. (2021). Predictive analytics of chemical material pricing. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/147902 https://hdl.handle.net/10356/147902 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Saini, Aditi Predictive analytics of chemical material pricing |
| title | Predictive analytics of chemical material pricing |
| title_full | Predictive analytics of chemical material pricing |
| title_fullStr | Predictive analytics of chemical material pricing |
| title_full_unstemmed | Predictive analytics of chemical material pricing |
| title_short | Predictive analytics of chemical material pricing |
| title_sort | predictive analytics of chemical material pricing |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/147902 |
| work_keys_str_mv | AT sainiaditi predictiveanalyticsofchemicalmaterialpricing |