Edited, memorised or added to reading queue

on 14-Nov-2024 (Thu)

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

Annotation 7103971200268

#RNN #ariadne #behaviour #consumer #deep-learning #priority #retail #simulation #synthetic-data
From Neural Network architectures perspective, close to our work is Deep Neural Network Ensembles for Time Series Classification [8]. In this paper, authors show how an ensemble of multiple Convolutional Neural Networks can improve upon the state-of-the-art performance of individual neural networks. They use 6 deep learning classifiers including Multi-Layer Perceptron, Fully Convolutional Neural Network, Residual Network, Encoder [20], Multi-Channels Deep Convolutional Neural Networks [29] and Time Convolutional Neural Network [28]. The first three were originally proposed in [24]. We propose the application of such architectures in the consumer choice world and apply the concept of entity embeddings [9] along with neural network architectures like Multi-Layer Perceptron, Long Short Term Memory (LSTM), Temporal Convolutional Networks (TCN) [13] and TCN-LSTM
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

pdf

cannot see any pdfs



Annotation 7666577575180

#deep-learning #keras #lstm #python #sequence
If your problem looks like a traditional autoregression type problem with the most relevant lag observations within a small window, then perhaps develop a baseline of performance with an MLP and sliding window before considering an LSTM
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
Think of the internal state of LSTMs as a handy internal variable to capture and provide context for making predictions. If your problem looks like a traditional autoregression type problem with the most relevant lag observations within a small window, then perhaps develop a baseline of performance with an MLP and sliding window before considering an LSTM.

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7666579410188

Tags
#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Question
As machine learning models become ubiquitous in our everyday lives, demand for explaining their predictions is growing [5, 16, 14]. In the context of behaviour prediction, we want to understand how previous consumer [...] influence model predictions
Answer
actions

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
dels become ubiquitous in our everyday lives, demand for explaining their predictions is growing [5, 16, 14]. In the context of behaviour prediction, we want to understand how previous consumer <span>actions influence model predictions <span>

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666581245196

Tags
#data-science #infrastructure
Question
Incidental complexity is a huge problem for real-world data science because we have to deal with such a high level of [...] complexity that distinguishing between real problems and imaginary problems becomes hard
Answer
inherent

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
Incidental complexity is a huge problem for real-world data science because we have to deal with such a high level of inherent complexity that distinguishing between real problems and imaginary problems becomes hard

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666583342348

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
Artificial feedforward neural networks (ANN) have also been shown to effectively predict household brand choices, as well as brand market shares (Agrawal & Schorling, 1996). Since brand choices can be modeled as sequential choices, and data complexity increases exponentially with the number of brands (with interaction effects), [...] neural networks offer suitable alternatives.
Answer
LSTM

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
ares (Agrawal & Schorling, 1996). Since brand choices can be modeled as sequential choices, and data complexity increases exponentially with the number of brands (with interaction effects), <span>LSTM neural networks offer suitable alternatives. <span>

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666585177356

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
While training a model, the analyst aims at setting the parameters and hyperparameters such that the model reaches optimal capacity (Goodfellow et al., 2016) and therefore maximizes the chances that the model will generalize well to [...].
Answer
unseen data

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
s at setting the parameters and hyperparameters such that the model reaches optimal capacity (Goodfellow et al., 2016) and therefore maximizes the chances that the model will generalize well to <span>unseen data. <span>

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666587012364

Tags
#deep-learning #keras #lstm #python #sequence
Question
The choice of activation function is most important for the output layer as it will define the [...] that predictions will take.
Answer
format

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
The choice of activation function is most important for the output layer as it will define the format that predictions will take.

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7666589371660

#recurrent-neural-networks #rnn
To make the predicted transaction sequences robust against sampling noise, we repeat this process for each customer several times and take the mean expected number of transactions in a given time step as our final result.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
wing a sample from the multinomial output distribution calculated by the bottom network layer; our model therefore does not produce point or interval estimates, each output is a simulated draw. <span>To make the predicted transaction sequences robust against sampling noise, we repeat this process for each customer several times and take the mean expected number of transactions in a given time step as our final result. We describe how this benefits the prediction accuracy in the Appendix <span>

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7666591206668

Tags
#recurrent-neural-networks #rnn
Question
We propose and implement a flexible methodological framework that provides marketing managers with highly accurate forecasts of fine granularity both in the short and in the long run. Our method also captures seasonal peaks and [...] dynamics and allows to differentiate between different customer groups
Answer
customer-level

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
e methodological framework that provides marketing managers with highly accurate forecasts of fine granularity both in the short and in the long run. Our method also captures seasonal peaks and <span>customer-level dynamics and allows to differentiate between different customer groups <span>

Original toplevel document (pdf)

cannot see any pdfs