Edited, memorised or added to reading queue

on 19-Jan-2023 (Thu)

Do you want BuboFlash to help you learning these things? Click here to log in or create user.

Annotation 7096409132300

#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data

Event-stream RNNs

We propose to model the behavior of consumers with RNNs. Consumer histories are inherently sequential and of varying lengths T , making RNNs a natural model choice. In e-commerce, available data sources and prediction scenarios often change, making the generality of RNNs appealing as no problem-specific feature engineering has to take place.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

pdf

cannot see any pdfs



Annotation 7103894916364

#feature-engineering #lstm #recurrent-neural-networks #rnn
All four customers in the figure have the same seniority (date of first purchase), recency (date of last purchase), and frequency (number of purchases). However, each of them has a visibly different transaction pattern. A response model relying exclusively on seniority, recency, and frequency would not be able to distinguish between customers who have similar featu res but different behavioral sequence.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

pdf

cannot see any pdfs



Annotation 7104163351820

#deep-learning #keras #lstm #python #sequence

7.1 The Stacked LSTM

The Stacked LSTM is a model that has multiple hidden LSTM layers where each layer contains multiple memory cells. We will refer to it as a Stacked LSTM here to differentiate it from the unstacked LSTM (Vanilla LSTM) and a variety of other extensions to the basic LSTM model.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

pdf

cannot see any pdfs



Flashcard 7559874743564

Tags
#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Question
All models are trained to [...] negative log-likelihood (NLL).
Answer
minimize

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
All models are trained to minimize negative log-likelihood (NLL).

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7559876316428

#deep-learning #keras #lstm #python #sequence
How to Convert Categorical Data to Numerical Data This involves two steps: 1. Integer Encoding. 2. One Hot Encoding.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
3.2.1 How to Convert Categorical Data to Numerical Data This involves two steps: 1. Integer Encoding. 2. One Hot Encoding. Integer Encoding As a first step, each unique category value is assigned an integer value. For example, red is 1, green is 2, and blue is 3. This is called label encoding or an integer

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7559879200012

#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
feature engineering: a fixed set of identifiers f i has to be designed to capture the essence of an individual consumer history. Only signals that are encoded in the feature vector can be picked up by the prediction model. Defining expressive features often requires both, domain knowledge as well as data-science intuition
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
ed machine learning methods like logistic regression take vectors f = (f 1 , . . . , f n ) of fixed length n as inputs. Applying these methods on consumer histories of arbitrary length requires <span>feature engineering: a fixed set of identifiers f i has to be designed to capture the essence of an individual consumer history. Only signals that are encoded in the feature vector can be picked up by the prediction model. Defining expressive features often requires both, domain knowledge as well as data-science intuition. <span>

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7559881821452

#deep-learning #keras #lstm #python #sequence
The internal state in LSTM layers is also accumulated when evaluating a network and when making predictions
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
The internal state in LSTM layers is also accumulated when evaluating a network and when making predictions. Therefore, if you are using a stateful LSTM, you must reset state after evaluating the network on a validation dataset or after making predictions

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7559885229324

#deep-learning #keras #lstm #python #sequence
The Stacked LSTM is a model that has multiple hidden LSTM layers where each layer contains multiple memory cells.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
7.1 The Stacked LSTM The Stacked LSTM is a model that has multiple hidden LSTM layers where each layer contains multiple memory cells. We will refer to it as a Stacked LSTM here to differentiate it from the unstacked LSTM (Vanilla LSTM) and a variety of other extensions to the basic LSTM model.

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7559888375052

#feature-engineering #lstm #recurrent-neural-networks #rnn
In machine learning, a feature refers to a variable that describes some aspect of individual data objects (Dong & Liu, 2018).
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
In machine learning, a feature refers to a variable that describes some aspect of individual data objects (Dong & Liu, 2018). Feature engineering has been used broadly to refer to multiple aspects of feature creation, extraction, and transformation. Essentially, it refers to the process of using domain knowled

Original toplevel document (pdf)

cannot see any pdfs