Edited, memorised or added to reading queue

on 13-Nov-2024 (Wed)

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

Annotation 7100409974028

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

Learning Machine Architecture

The proposed RNN model is consisted of one input layer, one hidden (recurrent) layer, and one output layer. The input layer is an auto-encoder which extracts features from inputs. The CLN, R, F, and M values for each customer at each time-step t are the input sequence to the RNN model presented in Figure 4. The R, F, and M value of the next time-step t + 1 is shown to the model as target through predefined time intervals. The time-step t can be set depending on the application. For example, for grocery stores it can be weekly or bi-weekly and for sports wear every season
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

pdf

cannot see any pdfs



Annotation 7103813127436

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

.. recurrent neural networks contain cycles that feed the network activations from a previous time step as inputs to the network to influence predictions at the current time step. These activations are stored in the internal states of the network which can in principle hold long-term temporal contextual information. This mechanism allows RNNs to exploit a dynamically changing contextual window over the input sequence history

— Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling, 2014
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

pdf

cannot see any pdfs



Annotation 7591156911372

#ML_in_Action #learning #machine #software-engineering
ML engineering applies a system around this staggering level of complexity. It uses a set of standards, tools, processes, and methodology that aims to minimize the chances of abandoned, misguided, or irrelevant work being done in an effort to solve a business problem or need.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
ML engineering applies a system around this staggering level of complexity. It uses a set of standards, tools, processes, and methodology that aims to minimize the chances of abandoned, misguided, or irrelevant work being done in an effort to solve a business problem or need. It, in essence, is the road map to creating ML-based systems that can be not only deployed to production, but also maintained and updated for years in the future, allowing businesses t

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7625289895180

Tags
#English #vocabulary
Question

[...]

adjective

not likely to upset or harm anyone

Answer
innocuous

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

Open it
innocuous adjective UK /ɪˈnɒkjuəs/ US not likely to upset or harm anyone






Annotation 7666481106188

#ML-engineering #ML_in_Action #learning #machine #software-engineering
Generally, these failures happen because the DS team is either inexperienced with solving a problem of the scale required (a technological or process-driven failure) or hasn’t fully understood the desired outcome from the business (a communication- driven failure)
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
to reach production. We’ll also discuss the solutions to each of these common failures and cover the processes that can significantly lower the chances of these factors derailing your projects. <span>Generally, these failures happen because the DS team is either inexperienced with solving a problem of the scale required (a technological or process-driven failure) or hasn’t fully understood the desired outcome from the business (a communication- driven failure). I’ve never seen this happen because of malicious intent. Rather, most ML projects are incredibly challenging, complex, and composed of algorithmic software tooling that is hard to expl

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7666482941196

Tags
#deep-learning #keras #lstm #python #sequence
Question
The [...] LSTM is a model that has multiple hidden LSTM layers
Answer
Stacked

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 Stacked LSTM is a model that has multiple hidden LSTM layers

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7666485038348

#recurrent-neural-networks #rnn
We show that incorporating contextual information in the model is straightforward and brings an additional boost in predictive accuracy. However, the model performance is already extremely strong when no context is available beyond the timing of the customer’s transactions. This is welcome news for firms that do not wish to collect personal information on principle, to avoid the questionable ethics of harvesting the ‘‘behavioral surplus”
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
for the marketing analyst, such as the lack of need for manual encoding of any features in the customer data, a simple optimization objective, and quick estimation on modern computer hardware. <span>We show that incorporating contextual information in the model is straightforward and brings an additional boost in predictive accuracy. However, the model performance is already extremely strong when no context is available beyond the timing of the customer’s transactions. This is welcome news for firms that do not wish to collect personal information on principle, to avoid the questionable ethics of harvesting the ‘‘behavioral surplus” (Zuboff, 2019): our work shows that this is feasible without a big loss of accuracy. <span>

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7666486873356

Tags
#causality #statistics
Question
Another way to see that the intervened node has no causal parents is that the intervened node is set to a [...], so it no longer depends on any of the variables it depends on in the observational setting (its parents)
Answer
constant value

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
Another way to see that the intervened node has no causal parents is that the intervened node is set to a constant value, so it no longer depends on any of the variables it depends on in the observational setting (its parents)

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666488708364

Tags
#recurrent-neural-networks #rnn
Question
customer defection in non-contractual business settings is by definition [...] by the firm and thus needs to be indirectly inferred from past transaction
Answer
unobserved

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
customer defection in non-contractual business settings is by definition unobserved by the firm and thus needs to be indirectly inferred from past transaction

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666490805516

Tags
#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Question
RNNs can be applied to predict future consumer behavior in regression and classification settings, for example, to predict interest in fashion brands or consumer [...] value.
Answer
lifetime

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
RNNs can be applied to predict future consumer behavior in regression and classification settings, for example, to predict interest in fashion brands or consumer lifetime value.

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666493164812

Tags
#deep-learning #keras #lstm #python #sequence
Question
Normalization is a [...] of the data from the original range so that all values are within the range of 0 and 1.
Answer
rescaling

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
Normalization is a rescaling of the data from the original range so that all values are within the range of 0 and 1.

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666494999820

Tags
#deep-learning #keras #lstm #python #sequence
Question
For a multiclass classification problem, the results may be in the form of [...] of probabilities (assuming a one hot encoded output variable) that may need to be converted to a single class output prediction using the argmax() NumPy function.
Answer
an array

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
For a multiclass classification problem, the results may be in the form of an array of probabilities (assuming a one hot encoded output variable) that may need to be converted to a single class output prediction using the argmax() NumPy function.

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7666497621260

#recurrent-neural-networks #rnn
non-contractual business settings (i.e., when the time at which a customer becomes inactive is unobserved by the firm)
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
aper presents a new approach that helps firms leverage the automatic feature extraction capabilities of a specific type of deep learning models when applied to customer transaction histories in <span>non-contractual business settings (i.e., when the time at which a customer becomes inactive is unobserved by the firm). We show how the proposed deep learning model improves on established models both in terms of individual-level accuracy and overall cohort-level bias. It also helps managers in capturin

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7666499456268

#recurrent-neural-networks #rnn
This paper presents a new approach that helps firms leverage the automatic feature extraction capabilities of a specific type of deep learning models when applied to customer transaction histories in non-contractual business settings
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
This paper presents a new approach that helps firms leverage the automatic feature extraction capabilities of a specific type of deep learning models when applied to customer transaction histories in non-contractual business settings (i.e., when the time at which a customer becomes inactive is unobserved by the firm). We show how the proposed deep learning model improves on established models both in terms of indivi

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7666502339852

#ML-engineering #ML_in_Action #learning #machine #software-engineering
Perhaps the most confusing and complex part of ML project work for newer teams is in how to build a cost-effective deployment strategy.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
Perhaps the most confusing and complex part of ML project work for newer teams is in how to build a cost-effective deployment strategy. If it’s underpowered, the prediction quality doesn’t matter (since the infrastructure can’t properly serve the predictions). If it’s overpowered, you’re effectively burning money on unu

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7666504961292

Tags
#ML_in_Action #learning #machine #software-engineering
Question
ML engineering applies a system around this staggering level of complexity. It uses a set of [...], tools, processes, and methodology that aims to minimize the chances of abandoned, misguided, or irrelevant work being done in an effort to solve a business problem or need.
Answer
standards

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
ML engineering applies a system around this staggering level of complexity. It uses a set of standards, tools, processes, and methodology that aims to minimize the chances of abandoned, misguided, or irrelevant work being done in an effort to solve a business problem or need. </sp

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666506796300

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
At each timestep, we submit relevant variables x, such as marketing actions (e.g., solicitations), customer behaviour (e.g., purchase occurrences), and seasonality indicators (e.g., month), in the form of a vector of [...] variables.
Answer
dummy

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
bmit relevant variables x, such as marketing actions (e.g., solicitations), customer behaviour (e.g., purchase occurrences), and seasonality indicators (e.g., month), in the form of a vector of <span>dummy variables. <span>

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7666508631308

#deep-learning #keras #lstm #python #sequence
Given that LSTMs operate on sequence data, it means that the addition of layers adds levels of abstraction of input observations over time. In effect, chunking observations over time or representing the problem at different time scales
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
Given that LSTMs operate on sequence data, it means that the addition of layers adds levels of abstraction of input observations over time. In effect, chunking observations over time or representing the problem at different time scales. ... building a deep RNN by stacking multiple recurrent hidden states on top of each other. This approach potentially allows the hidden state at each level to operate at different times

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7666510466316

Tags
#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Question
In principle, one could evaluate the logistic regression model at every single [...] in the consumer history to determine the influence of individual events
Answer
time-step

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
In principle, one could evaluate the logistic regression model at every single time-step in the consumer history to determine the influence of individual events

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666512301324

Tags
#deep-learning #keras #lstm #python #sequence
Question
as part of [...] your problem you must split long sequences into subsequences that are both long enough to capture relevant context for making predictions, but short enough to efficiently train the network
Answer
framing

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
as part of framing your problem you must split long sequences into subsequences that are both long enough to capture relevant context for making predictions, but short enough to efficiently train the netw

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666514136332

Tags
#deep-learning #keras #lstm #python #sequence
Question
[...] requires that you know or are able to accurately estimate the minimum and maximum observable values.
Answer
Normalization

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
Normalization requires that you know or are able to accurately estimate the minimum and maximum observable values.

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666515971340

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
Similar to our studies, we could encode [...] choices and the decision environment as we encoded solicitations and donations: as a multidimensional vector.
Answer
brand

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
Similar to our studies, we could encode brand choices and the decision environment as we encoded solicitations and donations: as a multidimensional vector.

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666517806348

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
In machine learning, a feature refers to a [...] that describes some aspect of individual data objects (Dong & Liu, 2018).
Answer
variable

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
In machine learning, a feature refers to a variable that describes some aspect of individual data objects (Dong & Liu, 2018).

Original toplevel document (pdf)

cannot see any pdfs