Time-Series Modeling with Neural Networks at Uber
Time-Series Modeling with Neural Networks at Uber
Nikolay Laptev
June 26, 2017
Outline
Motivation Modeling with Neural Nets Results & Discussion
Outline
Motivation
Special Event Prediction Applications Current solution
Modeling with Neural Nets Results & Discussion
Motivation: Special Event Forecasting
Application: Anomaly Detection
Internal dynamic configuration down.
High Uber Pool latency caused millions of users to drop
Intermittent fraud activity causes millions lost in revenue.
................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.
Related download
- anomaly detection for temporal data using long short term
- comparison of time series approaches applied to
- blood glucose level prediction as time series modeling
- hindsight an r based framework towards long short term
- chapter 9 how to develop encoder decoder lstms
- time series modeling with neural networks at uber
- long short term memory lstm recurrent neural network for
- adaboost lstm ensemble learning for financial time series
- mini course on long short term memory recurrent neural