Overview
On this submit we are going to practice an autoencoder to detect bank card fraud. We can even reveal find out how to practice Keras fashions within the cloud utilizing CloudML.
The idea of our mannequin would be the Kaggle Credit score Card Fraud Detection dataset, which was collected throughout a analysis collaboration of Worldline and the Machine Studying Group of ULB (Université Libre de Bruxelles) on huge information mining and fraud detection.
The dataset accommodates bank card transactions by European cardholders remodeled a two day interval in September 2013. There are 492 frauds out of 284,807 transactions. The dataset is very unbalanced, the optimistic class (frauds) account for less than 0.172% of all transactions.
Studying the information
After downloading the information from Kaggle, you possibly can learn it in to R with read_csv():
The enter variables include solely numerical values that are the results of a PCA transformation. To be able to protect confidentiality, no extra details about the unique options was supplied. The options V1, …, V28 have been obtained with PCA. There are nevertheless 2 options (Time and Quantity) that weren’t remodeled.
Time is the seconds elapsed between every transaction and the primary transaction within the dataset. Quantity is the transaction quantity and may very well be used for cost-sensitive studying. The Class variable takes worth 1 in case of fraud and 0 in any other case.
Autoencoders
Since solely 0.172% of the observations are frauds, we have now a extremely unbalanced classification drawback. With this type of drawback, conventional classification approaches often don’t work very nicely as a result of we have now solely a really small pattern of the rarer class.
An autoencoder is a neural community that’s used to study a illustration (encoding) for a set of knowledge, usually for the aim of dimensionality discount. For this drawback we are going to practice an autoencoder to encode non-fraud observations from our coaching set. Since frauds are presupposed to have a distinct distribution then regular transactions, we count on that our autoencoder could have larger reconstruction errors on frauds then on regular transactions. Which means we are able to use the reconstruction error as a amount that signifies if a transaction is fraudulent or not.
If you wish to study extra about autoencoders, a great place to begin is that this video from Larochelle on YouTube and Chapter 14 from the Deep Studying e book by Goodfellow et al.
Visualization
For an autoencoder to work nicely we have now a powerful preliminary assumption: that the distribution of variables for regular transactions is completely different from the distribution for fraudulent ones. Let’s make some plots to confirm this. Variables have been remodeled to a [0,1] interval for plotting.
We are able to see that distributions of variables for fraudulent transactions are very completely different then from regular ones, apart from the Time variable, which appears to have the very same distribution.
Preprocessing
Earlier than the modeling steps we have to do some preprocessing. We’ll break up the dataset into practice and check units after which we are going to Min-max normalize our information (that is performed as a result of neural networks work a lot better with small enter values). We can even take away the Time variable because it has the very same distribution for regular and fraudulent transactions.
Based mostly on the Time variable we are going to use the primary 200,000 observations for coaching and the remaining for testing. That is good observe as a result of when utilizing the mannequin we wish to predict future frauds primarily based on transactions that occurred earlier than.
Now let’s work on normalization of inputs. We created 2 features to assist us. The primary one will get descriptive statistics concerning the dataset which can be used for scaling. Then we have now a perform to carry out the min-max scaling. It’s necessary to notice that we utilized the identical normalization constants for coaching and check units.
library(purrr)
#' Will get descriptive statistics for each variable within the dataset.
get_desc <- perform(x) {
map(x, ~record(
min = min(.x),
max = max(.x),
imply = imply(.x),
sd = sd(.x)
))
}
#' Given a dataset and normalization constants it is going to create a min-max normalized
#' model of the dataset.
normalization_minmax <- perform(x, desc) {
map2_dfc(x, desc, ~(.x - .y$min)/(.y$max - .y$min))
}Now let’s create normalized variations of our datasets. We additionally remodeled our information frames to matrices since that is the format anticipated by Keras.
We’ll now outline our mannequin in Keras, a symmetric autoencoder with 4 dense layers.
library(keras)
mannequin <- keras_model_sequential()
mannequin %>%
layer_dense(models = 15, activation = "tanh", input_shape = ncol(x_train)) %>%
layer_dense(models = 10, activation = "tanh") %>%
layer_dense(models = 15, activation = "tanh") %>%
layer_dense(models = ncol(x_train))
abstract(mannequin)___________________________________________________________________________________
Layer (kind) Output Form Param #
===================================================================================
dense_1 (Dense) (None, 15) 450
___________________________________________________________________________________
dense_2 (Dense) (None, 10) 160
___________________________________________________________________________________
dense_3 (Dense) (None, 15) 165
___________________________________________________________________________________
dense_4 (Dense) (None, 29) 464
===================================================================================
Complete params: 1,239
Trainable params: 1,239
Non-trainable params: 0
___________________________________________________________________________________We’ll then compile our mannequin, utilizing the imply squared error loss and the Adam optimizer for coaching.
mannequin %>% compile(
loss = "mean_squared_error",
optimizer = "adam"
)Coaching the mannequin
We are able to now practice our mannequin utilizing the match() perform. Coaching the mannequin is fairly quick (~ 14s per epoch on my laptop computer). We’ll solely feed to our mannequin the observations of regular (non-fraudulent) transactions.
We’ll use callback_model_checkpoint() so as to save our mannequin after every epoch. By passing the argument save_best_only = TRUE we are going to carry on disk solely the epoch with smallest loss worth on the check set.
We can even use callback_early_stopping() to cease coaching if the validation loss stops lowering for five epochs.
checkpoint <- callback_model_checkpoint(
filepath = "mannequin.hdf5",
save_best_only = TRUE,
interval = 1,
verbose = 1
)
early_stopping <- callback_early_stopping(persistence = 5)
mannequin %>% match(
x = x_train[y_train == 0,],
y = x_train[y_train == 0,],
epochs = 100,
batch_size = 32,
validation_data = record(x_test[y_test == 0,], x_test[y_test == 0,]),
callbacks = record(checkpoint, early_stopping)
)Prepare on 199615 samples, validate on 84700 samples
Epoch 1/100
199615/199615 [==============================] - 17s 83us/step - loss: 0.0036 - val_loss: 6.8522e-04d from inf to 0.00069, saving mannequin to mannequin.hdf5
Epoch 2/100
199615/199615 [==============================] - 17s 86us/step - loss: 4.7817e-04 - val_loss: 4.7266e-04d from 0.00069 to 0.00047, saving mannequin to mannequin.hdf5
Epoch 3/100
199615/199615 [==============================] - 19s 94us/step - loss: 3.7753e-04 - val_loss: 4.2430e-04d from 0.00047 to 0.00042, saving mannequin to mannequin.hdf5
Epoch 4/100
199615/199615 [==============================] - 19s 94us/step - loss: 3.3937e-04 - val_loss: 4.0299e-04d from 0.00042 to 0.00040, saving mannequin to mannequin.hdf5
Epoch 5/100
199615/199615 [==============================] - 19s 94us/step - loss: 3.2259e-04 - val_loss: 4.0852e-04 enhance
Epoch 6/100
199615/199615 [==============================] - 18s 91us/step - loss: 3.1668e-04 - val_loss: 4.0746e-04 enhance
...After coaching we are able to get the ultimate loss for the check set by utilizing the consider() fucntion.
loss <- consider(mannequin, x = x_test[y_test == 0,], y = x_test[y_test == 0,])
loss loss
0.0003534254 Tuning with CloudML
We might be able to get higher outcomes by tuning our mannequin hyperparameters. We are able to tune, for instance, the normalization perform, the educational price, the activation features and the dimensions of hidden layers. CloudML makes use of Bayesian optimization to tune hyperparameters of fashions as described in this weblog submit.
We are able to use the cloudml bundle to tune our mannequin, however first we have to put together our venture by making a coaching flag for every hyperparameter and a tuning.yml file that can inform CloudML what parameters we wish to tune and the way.
The total script used for coaching on CloudML will be discovered at https://github.com/dfalbel/fraud-autoencoder-example. Crucial modifications to the code have been including the coaching flags:
FLAGS <- flags(
flag_string("normalization", "minmax", "One among minmax, zscore"),
flag_string("activation", "relu", "One among relu, selu, tanh, sigmoid"),
flag_numeric("learning_rate", 0.001, "Optimizer Studying Price"),
flag_integer("hidden_size", 15, "The hidden layer measurement")
)We then used the FLAGS variable contained in the script to drive the hyperparameters of the mannequin, for instance:
mannequin %>% compile(
optimizer = optimizer_adam(lr = FLAGS$learning_rate),
loss = 'mean_squared_error',
)We additionally created a tuning.yml file describing how hyperparameters needs to be diverse throughout coaching, in addition to what metric we wished to optimize (on this case it was the validation loss: val_loss).
tuning.yml
trainingInput:
scaleTier: CUSTOM
masterType: standard_gpu
hyperparameters:
objective: MINIMIZE
hyperparameterMetricTag: val_loss
maxTrials: 10
maxParallelTrials: 5
params:
- parameterName: normalization
kind: CATEGORICAL
categoricalValues: [zscore, minmax]
- parameterName: activation
kind: CATEGORICAL
categoricalValues: [relu, selu, tanh, sigmoid]
- parameterName: learning_rate
kind: DOUBLE
minValue: 0.000001
maxValue: 0.1
scaleType: UNIT_LOG_SCALE
- parameterName: hidden_size
kind: INTEGER
minValue: 5
maxValue: 50
scaleType: UNIT_LINEAR_SCALEWe describe the kind of machine we wish to use (on this case a standard_gpu occasion), the metric we wish to decrease whereas tuning, and the the utmost variety of trials (i.e. variety of mixtures of hyperparameters we wish to check). We then specify how we wish to range every hyperparameter throughout tuning.
You’ll be able to study extra concerning the tuning.yml file on the Tensorflow for R documentation and at Google’s official documentation on CloudML.
Now we’re able to ship the job to Google CloudML. We are able to do that by operating:
library(cloudml)
cloudml_train("practice.R", config = "tuning.yml")The cloudml bundle takes care of importing the dataset and putting in any R bundle dependencies required to run the script on CloudML. In case you are utilizing RStudio v1.1 or larger, it is going to additionally help you monitor your job in a background terminal. It’s also possible to monitor your job utilizing the Google Cloud Console.
After the job is completed we are able to acquire the job outcomes with:
It will copy the recordsdata from the job with the very best val_loss efficiency on CloudML to your native system and open a report summarizing the coaching run.
Since we used a callback to avoid wasting mannequin checkpoints throughout coaching, the mannequin file was additionally copied from Google CloudML. Recordsdata created throughout coaching are copied to the “runs” subdirectory of the working listing from which cloudml_train() known as. You’ll be able to decide this listing for the newest run with:
[1] runs/cloudml_2018_01_23_221244595-03It’s also possible to record all earlier runs and their validation losses with:
ls_runs(order = metric_val_loss, lowering = FALSE) run_dir metric_loss metric_val_loss
1 runs/2017-12-09T21-01-11Z 0.2577 0.1482
2 runs/2017-12-09T21-00-11Z 0.2655 0.1505
3 runs/2017-12-09T19-59-44Z 0.2597 0.1402
4 runs/2017-12-09T19-56-48Z 0.2610 0.1459
Use View(ls_runs()) to view all columnsIn our case the job downloaded from CloudML was saved to runs/cloudml_2018_01_23_221244595-03/, so the saved mannequin file is on the market at runs/cloudml_2018_01_23_221244595-03/mannequin.hdf5. We are able to now use our tuned mannequin to make predictions.
Making predictions
Now that we skilled and tuned our mannequin we’re able to generate predictions with our autoencoder. We have an interest within the MSE for every statement and we count on that observations of fraudulent transactions could have larger MSE’s.
First, let’s load our mannequin.
mannequin <- load_model_hdf5("runs/cloudml_2018_01_23_221244595-03/mannequin.hdf5",
compile = FALSE)Now let’s calculate the MSE for the coaching and check set observations.
An excellent measure of mannequin efficiency in extremely unbalanced datasets is the Space Beneath the ROC Curve (AUC). AUC has a pleasant interpretation for this drawback, it’s the likelihood {that a} fraudulent transaction could have larger MSE then a standard one. We are able to calculate this utilizing the Metrics bundle, which implements all kinds of widespread machine studying mannequin efficiency metrics.
[1] 0.9546814
[1] 0.9403554To make use of the mannequin in observe for making predictions we have to discover a threshold (okay) for the MSE, then if if (MSE > okay) we think about that transaction a fraud (in any other case we think about it regular). To outline this worth it’s helpful to take a look at precision and recall whereas various the brink (okay).
possible_k <- seq(0, 0.5, size.out = 100)
precision <- sapply(possible_k, perform(okay) {
predicted_class <- as.numeric(mse_test > okay)
sum(predicted_class == 1 & y_test == 1)/sum(predicted_class)
})
qplot(possible_k, precision, geom = "line")
+ labs(x = "Threshold", y = "Precision")
recall <- sapply(possible_k, perform(okay) {
predicted_class <- as.numeric(mse_test > okay)
sum(predicted_class == 1 & y_test == 1)/sum(y_test)
})
qplot(possible_k, recall, geom = "line")
+ labs(x = "Threshold", y = "Recall")
An excellent place to begin can be to decide on the brink with most precision however we may additionally base our choice on how a lot cash we’d lose from fraudulent transactions.
Suppose every guide verification of fraud prices us $1 but when we don’t confirm a transaction and it’s a fraud we are going to lose this transaction quantity. Let’s discover for every threshold worth how a lot cash we’d lose.
cost_per_verification <- 1
lost_money <- sapply(possible_k, perform(okay) {
predicted_class <- as.numeric(mse_test > okay)
sum(cost_per_verification * predicted_class + (predicted_class == 0) * y_test * df_test$Quantity)
})
qplot(possible_k, lost_money, geom = "line") + labs(x = "Threshold", y = "Misplaced Cash")
We are able to discover the very best threshold on this case with:
[1] 0.005050505If we would have liked to manually confirm all frauds, it will price us ~$13,000. Utilizing our mannequin we are able to cut back this to ~$2,500.
