Show simple item record

dc.contributor.authorKakooza, Abraham Jerry
dc.date.accessioned2021-02-11T08:58:11Z
dc.date.available2021-02-11T08:58:11Z
dc.date.issued2021-02-03
dc.identifier.citationKakooza, A. J. (2021). Design of a machine learning based system for pharmaceutical purchases. Unpublished undergraduate dissertation. Makerere University. Kampala, Uganda.en_US
dc.identifier.urihttp://hdl.handle.net/20.500.12281/8769
dc.descriptionA report submitted in partial fulfillment of the requirements for the Degree of Bachelor of Science in Telecommunications Engineering at Makerere Universityen_US
dc.description.abstractTo obtain inherent laws from vast amounts of pharmaceutical sales data and to provide valuable information to pharmacy managers, this work validates di erent methods and approaches to perform a sales forecast. Part of the data is used to train a neural network algorithm, with backpropagation for some methods, step by step, where shallow nets face selected scenarios, with di erent space-time data considerations. In each method, by using a sum of square di erences, and a peak search procedure, a reasonable quality in the obtained abstract representations is pursued. First, an auto-encoder is trained to develop in its hidden layer neural data abstractions about a random-moving window. Thereafter by using the abstraction of the net plus recently captured information, a second shallow net is trained to produce its own one-day ahead estimates, using new timing and data procedures. After training, the whole stacked system's performance is compared with the naive forecast scenario's mean square error and if it's a better value, the method is used to produce stable daily forecasting for assorted products and periods. The system has been tested in real-time with real data.en_US
dc.language.isoenen_US
dc.subjectMachine learning based systemen_US
dc.subjectPharmaceutical purchases.en_US
dc.titleDesign of a machine learning based system for pharmaceutical purchases.en_US
dc.typeThesisen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record