Enhancement of Consumption Forecasting by Customers’ Behavioral Predictability Segregation
The easiest approach to customer activity forecasting involves using the whole available and applicable population of customers that a certain data set contains. The drawback of this simple technique is twofold: the set could be too big, and it could contain customers of very different peculiarities...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Engineering Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4591/39/1/61 |
| _version_ | 1797580291598974976 |
|---|---|
| author | Maria Koshkareva Anton Kovantsev |
| author_facet | Maria Koshkareva Anton Kovantsev |
| author_sort | Maria Koshkareva |
| collection | DOAJ |
| description | The easiest approach to customer activity forecasting involves using the whole available and applicable population of customers that a certain data set contains. The drawback of this simple technique is twofold: the set could be too big, and it could contain customers of very different peculiarities, which means that customers whose previous behavior is helpful for the forecast and whose one is not are mixed, and while the first performs a good-quality prediction, the second spoils it by adding noise. Hence, if we could choose the customers with good predictability and put aside the others <i>“as a shepherd divideth his sheep from the goats” (Matthew 25:32)</i>, we would solve both problems: less data volume and less noise; the principle is like ancient <i>“divide et impera”</i>. In our research, we developed the method of customers separation by predictability and its dynamics with the help of LSTM models. Our research shows that (1) customer separation helps to improve the forecasting quality of the whole population due to the decomposition of all clients’ time series, and (2) environmental instability such as pandemics or military action can be leveled out with incremental models. |
| first_indexed | 2024-03-10T22:48:03Z |
| format | Article |
| id | doaj.art-283c00be415240eda9ace4e0e75ec243 |
| institution | Directory Open Access Journal |
| issn | 2673-4591 |
| language | English |
| last_indexed | 2024-03-10T22:48:03Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Engineering Proceedings |
| spelling | doaj.art-283c00be415240eda9ace4e0e75ec2432023-11-19T10:31:01ZengMDPI AGEngineering Proceedings2673-45912023-07-013916110.3390/engproc2023039061Enhancement of Consumption Forecasting by Customers’ Behavioral Predictability SegregationMaria Koshkareva0Anton Kovantsev1Department of Digital Transformation, ITMO University, St. Petersburg 197101, RussiaNational Center for Cognitive Research, ITMO University, St. Petersburg 197101, RussiaThe easiest approach to customer activity forecasting involves using the whole available and applicable population of customers that a certain data set contains. The drawback of this simple technique is twofold: the set could be too big, and it could contain customers of very different peculiarities, which means that customers whose previous behavior is helpful for the forecast and whose one is not are mixed, and while the first performs a good-quality prediction, the second spoils it by adding noise. Hence, if we could choose the customers with good predictability and put aside the others <i>“as a shepherd divideth his sheep from the goats” (Matthew 25:32)</i>, we would solve both problems: less data volume and less noise; the principle is like ancient <i>“divide et impera”</i>. In our research, we developed the method of customers separation by predictability and its dynamics with the help of LSTM models. Our research shows that (1) customer separation helps to improve the forecasting quality of the whole population due to the decomposition of all clients’ time series, and (2) environmental instability such as pandemics or military action can be leveled out with incremental models.https://www.mdpi.com/2673-4591/39/1/61predictabilityconsumer behaviorincremental learning |
| spellingShingle | Maria Koshkareva Anton Kovantsev Enhancement of Consumption Forecasting by Customers’ Behavioral Predictability Segregation Engineering Proceedings predictability consumer behavior incremental learning |
| title | Enhancement of Consumption Forecasting by Customers’ Behavioral Predictability Segregation |
| title_full | Enhancement of Consumption Forecasting by Customers’ Behavioral Predictability Segregation |
| title_fullStr | Enhancement of Consumption Forecasting by Customers’ Behavioral Predictability Segregation |
| title_full_unstemmed | Enhancement of Consumption Forecasting by Customers’ Behavioral Predictability Segregation |
| title_short | Enhancement of Consumption Forecasting by Customers’ Behavioral Predictability Segregation |
| title_sort | enhancement of consumption forecasting by customers behavioral predictability segregation |
| topic | predictability consumer behavior incremental learning |
| url | https://www.mdpi.com/2673-4591/39/1/61 |
| work_keys_str_mv | AT mariakoshkareva enhancementofconsumptionforecastingbycustomersbehavioralpredictabilitysegregation AT antonkovantsev enhancementofconsumptionforecastingbycustomersbehavioralpredictabilitysegregation |