Building a Fraud Prediction Model with EvalML¶

In this demo, we will build an optimized fraud prediction model using EvalML. To optimize the pipeline, we will set up an objective function to minimize the percentage of total transaction value lost to fraud. At the end of this demo, we also show you how introducing the right objective during the training is over 4x better than using a generic machine learning metric like AUC.

[1]:

import evalml
from evalml import AutoMLSearch
from evalml.objectives import FraudCost

Configure “Cost of Fraud”¶

To optimize the pipelines toward the specific business needs of this model, we can set our own assumptions for the cost of fraud. These parameters are

retry_percentage - what percentage of customers will retry a transaction if it is declined?
interchange_fee - how much of each successful transaction do you collect?
fraud_payout_percentage - the percentage of fraud will you be unable to collect
amount_col - the column in the data the represents the transaction amount

Using these parameters, EvalML determines attempt to build a pipeline that will minimize the financial loss due to fraud.

[2]:

fraud_objective = FraudCost(retry_percentage=.5,
                            interchange_fee=.02,
                            fraud_payout_percentage=.75,
                            amount_col='amount')

Search for best pipeline¶

In order to validate the results of the pipeline creation and optimization process, we will save some of our data as the holdout set.

[3]:

X, y = evalml.demos.load_fraud(n_rows=1000)

             Number of Features
Boolean                       1
Categorical                   6
Numeric                       5

Number of training examples: 1000
Targets
False    85.90%
True     14.10%
Name: fraud, dtype: object

EvalML natively supports one-hot encoding. Here we keep 1 out of the 6 categorical columns to decrease computation time.

[4]:

cols_to_drop = ['datetime', 'expiration_date', 'country', 'region', 'provider']
for col in cols_to_drop:
    X.pop(col)

X_train, X_holdout, y_train, y_holdout = evalml.preprocessing.split_data(X, y, problem_type='binary', test_size=0.2, random_seed=0)

print(X.types)

                 Physical Type Logical Type Semantic Tag(s)
Data Column
card_id                  Int64      Integer     ['numeric']
store_id                 Int64      Integer     ['numeric']
amount                   Int64      Integer     ['numeric']
currency              category  Categorical    ['category']
customer_present       boolean      Boolean              []
lat                    float64       Double     ['numeric']
lng                    float64       Double     ['numeric']

Because the fraud labels are binary, we will use AutoMLSearch(X_train=X_train, y_train=y_train, problem_type='binary'). When we call .search(), the search for the best pipeline will begin.

[5]:

automl = AutoMLSearch(X_train=X_train, y_train=y_train,
                      problem_type='binary',
                      objective=fraud_objective,
                      additional_objectives=['auc', 'f1', 'precision'],
                      max_batches=1,
                      optimize_thresholds=True)

automl.search()

Generating pipelines to search over...
*****************************
* Beginning pipeline search *
*****************************

Optimizing for Fraud Cost.
Lower score is better.

Using SequentialEngine to train and score pipelines.
Searching up to 1 batches for a total of 9 pipelines.
Allowed model families: linear_model, extra_trees, xgboost, random_forest, decision_tree, catboost, lightgbm

Batch 1: (1/9) Mode Baseline Binary Classification P... Elapsed:00:00
Starting cross validation
Finished cross validation - mean Fraud Cost: 0.033
High coefficient of variation (cv >= 0.2) within cross validation scores. Mode Baseline Binary Classification Pipeline may not perform as estimated on unseen data.
Batch 1: (2/9) Decision Tree Classifier w/ Imputer +... Elapsed:00:00
Starting cross validation
Finished cross validation - mean Fraud Cost: 0.010
High coefficient of variation (cv >= 0.2) within cross validation scores. Decision Tree Classifier w/ Imputer + One Hot Encoder may not perform as estimated on unseen data.
Batch 1: (3/9) LightGBM Classifier w/ Imputer + One ... Elapsed:00:02
Starting cross validation
Finished cross validation - mean Fraud Cost: 0.002
Batch 1: (4/9) Extra Trees Classifier w/ Imputer + O... Elapsed:00:03
Starting cross validation
Finished cross validation - mean Fraud Cost: 0.002
Batch 1: (5/9) Elastic Net Classifier w/ Imputer + O... Elapsed:00:06
Starting cross validation
Finished cross validation - mean Fraud Cost: 0.002
Batch 1: (6/9) CatBoost Classifier w/ Imputer Elapsed:00:07
Starting cross validation
Finished cross validation - mean Fraud Cost: 0.002
Batch 1: (7/9) XGBoost Classifier w/ Imputer + One H... Elapsed:00:08
Starting cross validation
Finished cross validation - mean Fraud Cost: 0.002
Batch 1: (8/9) Random Forest Classifier w/ Imputer +... Elapsed:00:10
Starting cross validation
Finished cross validation - mean Fraud Cost: 0.002
Batch 1: (9/9) Logistic Regression Classifier w/ Imp... Elapsed:00:12
Starting cross validation
Finished cross validation - mean Fraud Cost: 0.002

Search finished after 00:15
Best pipeline: LightGBM Classifier w/ Imputer + One Hot Encoder
Best pipeline Fraud Cost: 0.002083

View rankings and select pipelines¶

Once the fitting process is done, we can see all of the pipelines that were searched, ranked by their score on the fraud detection objective we defined.

[6]:

automl.rankings

[6]:

	id	pipeline_name	score	validation_score	percent_better_than_baseline	high_variance_cv	parameters
0	2	LightGBM Classifier w/ Imputer + One Hot Encoder	0.002083	0.002101	3.081243	False	{'Imputer': {'categorical_impute_strategy': 'm...
1	3	Extra Trees Classifier w/ Imputer + One Hot En...	0.002083	0.002101	3.081243	False	{'Imputer': {'categorical_impute_strategy': 'm...
2	4	Elastic Net Classifier w/ Imputer + One Hot En...	0.002083	0.002101	3.081243	False	{'Imputer': {'categorical_impute_strategy': 'm...
3	5	CatBoost Classifier w/ Imputer	0.002083	0.002101	3.081243	False	{'Imputer': {'categorical_impute_strategy': 'm...
4	6	XGBoost Classifier w/ Imputer + One Hot Encoder	0.002083	0.002101	3.081243	False	{'Imputer': {'categorical_impute_strategy': 'm...
5	7	Random Forest Classifier w/ Imputer + One Hot ...	0.002083	0.002101	3.081243	False	{'Imputer': {'categorical_impute_strategy': 'm...
6	8	Logistic Regression Classifier w/ Imputer + On...	0.002083	0.002101	3.081243	False	{'Imputer': {'categorical_impute_strategy': 'm...
7	1	Decision Tree Classifier w/ Imputer + One Hot ...	0.010218	0.007469	2.267780	True	{'Imputer': {'categorical_impute_strategy': 'm...
8	0	Mode Baseline Binary Classification Pipeline	0.032895	0.022769	0.000000	True	{'Baseline Classifier': {'strategy': 'mode'}}

To select the best pipeline we can call automl.best_pipeline.

[7]:

best_pipeline = automl.best_pipeline

Describe pipelines¶

We can get more details about any pipeline created during the search process, including how it performed on other objective functions, by calling the describe_pipeline method and passing the id of the pipeline of interest.

[8]:

automl.describe_pipeline(automl.rankings.iloc[1]["id"])

*******************************************************
* Extra Trees Classifier w/ Imputer + One Hot Encoder *
*******************************************************

Problem Type: binary
Model Family: Extra Trees

Pipeline Steps
==============
1. Imputer
         * categorical_impute_strategy : most_frequent
         * numeric_impute_strategy : mean
         * categorical_fill_value : None
         * numeric_fill_value : None
2. One Hot Encoder
         * top_n : 10
         * features_to_encode : None
         * categories : None
         * drop : None
         * handle_unknown : ignore
         * handle_missing : error
3. Extra Trees Classifier
         * n_estimators : 100
         * max_features : auto
         * max_depth : 6
         * min_samples_split : 2
         * min_weight_fraction_leaf : 0.0
         * n_jobs : -1

Training
========
Training for binary problems.
Objective to optimize binary classification pipeline thresholds for: <evalml.objectives.fraud_cost.FraudCost object at 0x7f6a452c9b50>
Total training time (including CV): 2.2 seconds

Cross Validation
----------------
             Fraud Cost   AUC    F1  Precision # Training # Validation
0                 0.002 0.781 0.249      0.142    375.000      267.000
1                 0.002 0.831 0.249      0.142    375.000      267.000
2                 0.002 0.764 0.244      0.139    380.000      266.000
mean              0.002 0.792 0.248      0.141          -            -
std               0.000 0.035 0.003      0.002          -            -
coef of var       0.090 0.044 0.012      0.013          -            -

Evaluate on holdout data¶

Finally, since the best pipeline is already trained, we evaluate it on the holdout data.

Now, we can score the pipeline on the holdout data using both our fraud cost objective and the AUC (Area under the ROC Curve) objective.

[9]:

best_pipeline.score(X_holdout, y_holdout, objectives=["auc", fraud_objective])

[9]:

OrderedDict([('AUC', 0.8762458471760798), ('Fraud Cost', 0.03451909686569147)])

Why optimize for a problem-specific objective?¶

To demonstrate the importance of optimizing for the right objective, let’s search for another pipeline using AUC, a common machine learning metric. After that, we will score the holdout data using the fraud cost objective to see how the best pipelines compare.

[10]:

automl_auc = AutoMLSearch(X_train=X_train, y_train=y_train,
                          problem_type='binary',
                          objective='auc',
                          additional_objectives=['f1', 'precision'],
                          max_batches=1,
                          optimize_thresholds=True)

automl_auc.search()

Generating pipelines to search over...
*****************************
* Beginning pipeline search *
*****************************

Optimizing for AUC.
Greater score is better.

Using SequentialEngine to train and score pipelines.
Searching up to 1 batches for a total of 9 pipelines.
Allowed model families: linear_model, extra_trees, xgboost, random_forest, decision_tree, catboost, lightgbm

Batch 1: (1/9) Mode Baseline Binary Classification P... Elapsed:00:00
        Starting cross validation
        Finished cross validation - mean AUC: 0.500
Batch 1: (2/9) Decision Tree Classifier w/ Imputer +... Elapsed:00:00
        Starting cross validation
        Finished cross validation - mean AUC: 0.812
Batch 1: (3/9) LightGBM Classifier w/ Imputer + One ... Elapsed:00:00
        Starting cross validation
        Finished cross validation - mean AUC: 0.844
Batch 1: (4/9) Extra Trees Classifier w/ Imputer + O... Elapsed:00:01
        Starting cross validation
        Finished cross validation - mean AUC: 0.796
Batch 1: (5/9) Elastic Net Classifier w/ Imputer + O... Elapsed:00:02
        Starting cross validation
        Finished cross validation - mean AUC: 0.500
Batch 1: (6/9) CatBoost Classifier w/ Imputer           Elapsed:00:03
        Starting cross validation
        Finished cross validation - mean AUC: 0.830
Batch 1: (7/9) XGBoost Classifier w/ Imputer + One H... Elapsed:00:03
        Starting cross validation
        Finished cross validation - mean AUC: 0.842
Batch 1: (8/9) Random Forest Classifier w/ Imputer +... Elapsed:00:04
        Starting cross validation
        Finished cross validation - mean AUC: 0.833
Batch 1: (9/9) Logistic Regression Classifier w/ Imp... Elapsed:00:06
        Starting cross validation
        Finished cross validation - mean AUC: 0.739

Search finished after 00:06
Best pipeline: LightGBM Classifier w/ Imputer + One Hot Encoder
Best pipeline AUC: 0.844323

Like before, we can look at the rankings of all of the pipelines searched and pick the best pipeline.

[11]:

automl_auc.rankings

[11]:

	id	pipeline_name	score	validation_score	percent_better_than_baseline	high_variance_cv	parameters
0	2	LightGBM Classifier w/ Imputer + One Hot Encoder	0.844323	0.831878	34.432283	False	{'Imputer': {'categorical_impute_strategy': 'm...
1	6	XGBoost Classifier w/ Imputer + One Hot Encoder	0.842374	0.873592	34.237444	False	{'Imputer': {'categorical_impute_strategy': 'm...
2	7	Random Forest Classifier w/ Imputer + One Hot ...	0.832765	0.865663	33.276548	False	{'Imputer': {'categorical_impute_strategy': 'm...
3	5	CatBoost Classifier w/ Imputer	0.830093	0.883820	33.009291	False	{'Imputer': {'categorical_impute_strategy': 'm...
4	1	Decision Tree Classifier w/ Imputer + One Hot ...	0.811844	0.835210	31.184402	False	{'Imputer': {'categorical_impute_strategy': 'm...
5	3	Extra Trees Classifier w/ Imputer + One Hot En...	0.796378	0.806711	29.637797	False	{'Imputer': {'categorical_impute_strategy': 'm...
6	8	Logistic Regression Classifier w/ Imputer + On...	0.739222	0.762353	23.922221	False	{'Imputer': {'categorical_impute_strategy': 'm...
7	0	Mode Baseline Binary Classification Pipeline	0.500000	0.500000	0.000000	False	{'Baseline Classifier': {'strategy': 'mode'}}
8	4	Elastic Net Classifier w/ Imputer + One Hot En...	0.500000	0.500000	0.000000	False	{'Imputer': {'categorical_impute_strategy': 'm...

[12]:

best_pipeline_auc = automl_auc.best_pipeline

[13]:

# get the fraud score on holdout data
best_pipeline_auc.score(X_holdout, y_holdout,  objectives=["auc", fraud_objective])

[13]:

OrderedDict([('AUC', 0.8739617940199335), ('Fraud Cost', 0.02431400515651046)])

[14]:

# fraud score on fraud optimized again
best_pipeline.score(X_holdout, y_holdout, objectives=["auc", fraud_objective])

[14]:

OrderedDict([('AUC', 0.8762458471760798), ('Fraud Cost', 0.03451909686569147)])

When we optimize for AUC, we can see that the AUC score from this pipeline is better than the AUC score from the pipeline optimized for fraud cost. However, the losses due to fraud are over 3% of the total transaction amount when optimized for AUC and under 1% when optimized for fraud cost. As a result, we lose more than 2% of the total transaction amount by not optimizing for fraud cost specifically.

This happens because optimizing for AUC does not take into account the user-specified retry_percentage, interchange_fee, fraud_payout_percentage values. Thus, the best pipelines may produce the highest AUC but may not actually reduce the amount loss due to your specific type fraud.

This example highlights how performance in the real world can diverge greatly from machine learning metrics.

Tutorials Building a Lead Scoring Model with EvalML