Univerza na Primorskem Fakulteta za matematiko, naravoslovje in informacijske tehnologije
-->
SI | EN

Ponedeljkov seminar računalništva in informatike - Arhiv

2024 2023 2022 2021 2020 2019 2018 2017 2016 2015 2014 2013 2012
1 2 3 4 5 6 7 8 9 10 11 12

petek, 2. september 2022 Vanja MILESKI: Deep learning for churn prediction in retail using residual networks

V ponedeljek, 5. septembra 2022, bo ob 16.00 uri prek spletnih orodij na daljavo izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 5. september 2022 ob 16.00 na daljavo

-----------------------------------------
PREDAVATELJ: Vanja MILESKI
-----------------------------------------

After graduating from the Faculty of Computer and Information Science at the University of Ljubljana in 2015, Vanja Mileski started working at the Jožef Stefan Institute (JSI). He was a Master's student at the International Postgraduate School Jožef Stefan and a student researcher at the JSI. After finishing his Master's studies, he applied his knowledge of data mining in the private sector as a Data Scientist in the retail, telecommunications, banking, stock market and insurance sectors.
His current research interests include time-series classification, deep learning, ResNet and Inception architectures.

--------------------------------------------------------------------------------------------------------
NASLOV: Deep learning for churn prediction in retail using residual networks
--------------------------------------------------------------------------------------------------------

POVZETEK:

With the advancements in Convolutional Neural Network (CNN) architectures, residual networks (ResNets) have proven successful on time series data as well. Time series features can be viewed as one-dimensional vectors, using which which we can train a deeper network using a ResNet-like architecture. Churn prediction is the process of identifying people that will cease to be customers in the future. We implement a ResNet architecture on real-life data of customer shopping habits obtained from a large retailer in Slovenia and compare them to traditional ML techniques.

 

Seminar bo potekal v angleškem jeziku v Zoom "klepetalnici" na naslovu:

https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Vabljeni!