TCI

aidotse · Nov 23, 2023 · 3a0cdd2 · 3a0cdd2
1 parent 9978d63
commit 3a0cdd2
Show file tree

Hide file tree

Showing 45 changed files with 456 additions and 118 deletions.
diff --git a/AMLsim/Dockerfile b/AMLsim/Dockerfile
@@ -37,4 +37,4 @@ COPY index.html index.html
 COPY pom.xml pom.xml
 COPY target target
 
-ENTRYPOINT ["sh", "scripts/run.sh"]
+ENTRYPOINT ["sh", "scripts/run.sh"]
diff --git a/AMLsim/paramFiles/10K_accts.zip b/AMLsim/paramFiles/10K_accts.zip
diff --git a/AMLsim/paramFiles/10K_accts/accounts.csv b/AMLsim/paramFiles/10K_accts/accounts.csv
@@ -1,13 +1,13 @@
 count,min_balance,max_balance,country,business_type,bank_id
-2768,10000,50000,SWE,I,swedbank
-1347,10000,50000,SWE,I,handelsbanken
-371,10000,50000,SWE,I,seb
-2694,10000,50000,SWE,I,nordea
-104,10000,50000,SWE,I,danske
-458,10000,50000,SWE,I,länsförsäkringar
-748,10000,50000,SWE,I,ica
-362,10000,50000,SWE,I,sparbanken
-23,10000,50000,SWE,I,ålandsbanken
-224,10000,50000,SWE,I,marginalen
-625,10000,50000,SWE,I,svea
-276,10000,50000,SWE,I,skandia
+2768,10000,20000,SWE,I,swedbank
+1347,5000,10000,SWE,I,handelsbanken
+371,5000,10000,SWE,I,seb
+2694,5000,10000,SWE,I,nordea
+104,5000,10000,SWE,I,danske
+458,5000,10000,SWE,I,länsförsäkringar
+748,5000,10000,SWE,I,ica
+362,5000,10000,SWE,I,sparbanken
+23,5000,10000,SWE,I,ålandsbanken
+224,5000,10000,SWE,I,marginalen
+625,5000,10000,SWE,I,svea
+276,5000,10000,SWE,I,skandia
diff --git a/AMLsim/paramFiles/10K_accts/alertPatterns.csv b/AMLsim/paramFiles/10K_accts/alertPatterns.csv
@@ -1,20 +1,20 @@
 count,type,schedule_id,min_accounts,max_accounts,min_amount,max_amount,min_period,max_period,bank_id,is_sar,source_type
-1,fan_out,2,7,7,100,1000,1,365,,True,CASH
-1,fan_in,2,7,7,100,1000,1,365,,True,CASH
-1,cycle,2,7,7,100,1000,1,365,,True,CASH
-1,bipartite,2,7,7,100,1000,1,365,,True,CASH
-1,stack,2,7,7,100,1000,1,365,,True,CASH
-1,scatter_gather,2,7,7,100,1000,1,365,,True,CASH
-1,gather_scatter,2,7,7,100,1000,1,365,,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,swedbank,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,handelsbanken,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,seb,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,nordea,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,danske,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,länsförsäkringar,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,ica,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,sparbanken,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,ålandsbanken,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,marginalen,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,svea,True,CASH
-1,fan_in,2,4,4,100,1000,1,365,skandia,True,CASH
+1,fan_out,2,7,7,100,1000,1,168,,True,CASH
+1,fan_in,2,7,7,100,1000,1,168,,True,CASH
+1,cycle,2,7,7,100,1000,1,168,,True,CASH
+1,bipartite,2,7,7,100,1000,1,168,,True,CASH
+1,stack,2,7,7,100,1000,1,168,,True,CASH
+1,scatter_gather,2,7,7,100,1000,1,168,,True,CASH
+1,gather_scatter,2,7,7,100,1000,1,168,,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,swedbank,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,handelsbanken,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,seb,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,nordea,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,danske,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,länsförsäkringar,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,ica,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,sparbanken,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,ålandsbanken,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,marginalen,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,svea,True,CASH
+1,fan_in,2,4,4,100,1000,1,168,skandia,True,CASH
diff --git a/AMLsim/paramFiles/10K_accts/conf.json b/AMLsim/paramFiles/10K_accts/conf.json
@@ -2,26 +2,25 @@
   "general": {
     "random_seed": 0,
     "simulation_name": "10K_accts",
-    "total_steps": 367,
-    "base_date": "2023-01-01"
+    "total_steps": 170
   },
   "default": {
     "min_amount": 1,
     "max_amount": 150000,
     "mean_amount": 637,
-    "std_amount": 300,
-    "mean_amount_sar": 1000,
-    "std_amount_sar": 300,
+    "std_amount": 3000,
+    "mean_amount_sar": 2000,
+    "std_amount_sar": 3000,
     "prob_income": 0.0,
     "mean_income": 0.0,
     "std_income": 0.0,
     "prob_income_sar": 0.0,
     "mean_income_sar": 0.0,
     "std_income_sar": 0.0,
-    "mean_outcome": 1000,
-    "std_outcome": 500,
-    "mean_outcome_sar": 1000,
-    "std_outcome_sar": 500,
+    "mean_outcome": 200.0,
+    "std_outcome": 500.0,
+    "mean_outcome_sar": 0.0,
+    "std_outcome_sar": 0.0,
     "mean_phone_change_frequency": 1460,
     "std_phone_change_frequency": 365,
     "mean_phone_change_frequency_sar": 365,
@@ -30,31 +29,7 @@
     "std_bank_change_frequency": 1,
     "mean_bank_change_frequency_sar": 1460,
     "std_bank_change_frequency_sar": 1,
-    "min_balance": 100000,
-    "max_balance": 200000,
-    "start_step": -1,
-    "end_step": -1,
-    "start_range": -1,
-    "end_range": -1,
-    "transaction_model": 1,
-    "margin_ratio": 0.1,
-    "bank_id": "default",
-    "cash_in": {
-      "normal_interval": 100,
-      "fraud_interval": 50,
-      "normal_min_amount": 50,
-      "normal_max_amount": 100,
-      "fraud_min_amount": 500,
-      "fraud_max_amount": 1000
-    },
-    "cash_out": {
-      "normal_interval": 10,
-      "fraud_interval": 100,
-      "normal_min_amount": 10,
-      "normal_max_amount": 100,
-      "fraud_min_amount": 1000,
-      "fraud_max_amount": 2000
-    }
+    "margin_ratio": 0.1
   },
   "input": {
     "directory": "paramFiles/10K_accts",
@@ -75,39 +50,14 @@
   },
   "output": {
     "directory": "outputs",
-    "accounts": "accounts.csv",
-    "transactions": "transactions.csv",
-    "cash_transactions": "cash_tx.csv",
-    "alert_members": "alert_accounts.csv",
-    "alert_transactions": "alert_transactions.csv",
-    "sar_accounts": "sar_accounts.csv",
-    "party_individuals": "individuals-bulkload.csv",
-    "party_organizations": "organizations-bulkload.csv",
-    "account_mapping": "accountMapping.csv",
-    "resolved_entities": "resolvedentities.csv",
-    "transaction_log": "tx_log.csv",
-    "counter_log": "tx_count.csv",
-    "diameter_log": "diameter.csv"
+    "transaction_log": "tx_log.csv"
   },
   "graph_generator": {
-    "degree_threshold": 1,
-    "high_risk_countries": "",
-    "high_risk_business": ""
+    "degree_threshold": 1
   },
   "simulator": {
-    "compute_diameter": false,
     "transaction_limit": 100000,
     "transaction_interval": 7,
-    "sar_interval": 7,
-    "sar_balance_ratio": 1.0,
-    "numBranches": 1000
-  },
-  "visualizer": {
-    "degree": "deg.png",
-    "wcc": "wcc.png",
-    "alert": "alert.png",
-    "count": "count.png",
-    "clustering": "cc.png",
-    "diameter": "diameter.png"
+    "sar_interval": 7
   }
 }
diff --git a/AMLsim/paramFiles/10K_accts/conf_old.json b/AMLsim/paramFiles/10K_accts/conf_old.json
@@ -0,0 +1,113 @@
+{
+  "general": {
+    "random_seed": 0,
+    "simulation_name": "10K_accts",
+    "total_steps": 732,
+    "base_date": "2023-01-01"
+  },
+  "default": {
+    "min_amount": 1,
+    "max_amount": 150000,
+    "mean_amount": 637,
+    "std_amount": 1800,
+    "mean_amount_sar": 2000,
+    "std_amount_sar": 1800,
+    "prob_income": 0.0,
+    "mean_income": 0.0,
+    "std_income": 0.0,
+    "prob_income_sar": 0.0,
+    "mean_income_sar": 0.0,
+    "std_income_sar": 0.0,
+    "mean_outcome": 1000,
+    "std_outcome": 500,
+    "mean_outcome_sar": 1000,
+    "std_outcome_sar": 500,
+    "mean_phone_change_frequency": 1460,
+    "std_phone_change_frequency": 365,
+    "mean_phone_change_frequency_sar": 365,
+    "std_phone_change_frequency_sar": 182,
+    "mean_bank_change_frequency": 1460,
+    "std_bank_change_frequency": 1,
+    "mean_bank_change_frequency_sar": 1460,
+    "std_bank_change_frequency_sar": 1,
+    "min_balance": 100000,
+    "max_balance": 200000,
+    "start_step": -1,
+    "end_step": -1,
+    "start_range": -1,
+    "end_range": -1,
+    "transaction_model": 1,
+    "margin_ratio": 0.1,
+    "bank_id": "default",
+    "cash_in": {
+      "normal_interval": 100,
+      "fraud_interval": 50,
+      "normal_min_amount": 50,
+      "normal_max_amount": 100,
+      "fraud_min_amount": 500,
+      "fraud_max_amount": 1000
+    },
+    "cash_out": {
+      "normal_interval": 10,
+      "fraud_interval": 100,
+      "normal_min_amount": 10,
+      "normal_max_amount": 100,
+      "fraud_min_amount": 1000,
+      "fraud_max_amount": 2000
+    }
+  },
+  "input": {
+    "directory": "paramFiles/10K_accts",
+    "schema": "schema.json",
+    "accounts": "accounts.csv",
+    "alert_patterns": "alertPatterns.csv",
+    "normal_models": "normalModels.csv",
+    "degree": "degree.csv",
+    "transaction_type": "transactionType.csv",
+    "is_aggregated_accounts": true
+  },
+  "temporal": {
+    "directory": "tmp",
+    "transactions": "transactions.csv",
+    "accounts": "accounts.csv",
+    "alert_members": "alert_members.csv",
+    "normal_models": "normal_models.csv"
+  },
+  "output": {
+    "directory": "outputs",
+    "accounts": "accounts.csv",
+    "transactions": "transactions.csv",
+    "cash_transactions": "cash_tx.csv",
+    "alert_members": "alert_accounts.csv",
+    "alert_transactions": "alert_transactions.csv",
+    "sar_accounts": "sar_accounts.csv",
+    "party_individuals": "individuals-bulkload.csv",
+    "party_organizations": "organizations-bulkload.csv",
+    "account_mapping": "accountMapping.csv",
+    "resolved_entities": "resolvedentities.csv",
+    "transaction_log": "tx_log.csv",
+    "counter_log": "tx_count.csv",
+    "diameter_log": "diameter.csv"
+  },
+  "graph_generator": {
+    "degree_threshold": 1,
+    "high_risk_countries": "",
+    "high_risk_business": ""
+  },
+  "simulator": {
+    "compute_diameter": false,
+    "transaction_limit": 100000,
+    "transaction_interval": 7,
+    "sar_interval": 7,
+    "sar_balance_ratio": 1.0,
+    "numBranches": 1000
+  },
+  "visualizer": {
+    "degree": "deg.png",
+    "wcc": "wcc.png",
+    "alert": "alert.png",
+    "count": "count.png",
+    "clustering": "cc.png",
+    "diameter": "diameter.png"
+  }
+}
diff --git a/AMLsim/paramFiles/10K_accts/normalModels.csv b/AMLsim/paramFiles/10K_accts/normalModels.csv
@@ -1,7 +1,15 @@
 count,type,schedule_id,min_accounts,max_accounts,min_period,max_period,bank_id
-5000,single,2,1,1,1,365,
-5000,fan_out,2,4,4,1,365,
-5000,fan_in,2,4,4,1,365,
-5000,forward,2,3,3,1,365,
-5000,mutual,2,2,2,1,365,
-5000,periodical,2,2,2,1,365,
+3000,single,2,1,1,1,168,
+3000,fan_out,2,4,4,1,168,
+3000,fan_in,2,4,4,1,168,
+3000,forward,2,3,3,1,168,
+3000,mutual,2,2,2,1,168,
+3000,periodical,2,2,2,1,168,
+1000,single,0,1,1,1,168,handelsbanken
+3000,fan_out,1,4,4,1,168,handelsbanken
+3000,fan_in,2,4,4,1,168,handelsbanken
+3000,forward,3,3,3,1,168,handelsbanken
+3000,mutual,2,2,2,1,168,handelsbanken
+3000,periodical,2,2,2,1,168,handelsbanken
+30,fan_out,3,40,40,1,168,
+30,fan_in,3,40,40,1,168,
diff --git a/AMLsim/scripts/generate_scalefree.py b/AMLsim/scripts/generate_scalefree.py
@@ -92,7 +92,7 @@ def powerlaw_cluster_generator(_n, _edge_factor):
     print("Number of vertices: %d" % g.number_of_nodes())  # Number of vertices (accounts)
     print("Number of edges: %d" % g.number_of_edges())  # Number of edges (transactions)
 
-    #out_deg = Counter(g.out_degree().values())
+    #out_deg = Counter(g.out_degree().values()) # TODO: fix so degree.csv has aggretgates
     #in_deg = Counter(g.in_degree().values())
 
     #keys = set(sorted(list(in_deg.keys()) + list(out_deg.keys())))