Merge branch 'feature/20250111-update-rank683' of algorithm/ad-engine into master

ad-engine-commons/src/main/java/com/tzld/piaoquan/ad/engine/commons/math/Const.java

@@ -0,0 +1,5 @@
+package com.tzld.piaoquan.ad.engine.commons.math;
+
+public class Const {
+    public static final double WILSON_ZSCORE = 1.96;
+}

ad-engine-commons/src/main/java/com/tzld/piaoquan/ad/engine/commons/util/NumUtil.java

@@ -13,6 +13,17 @@ public class NumUtil {
         return d1 / d2;
     }
 
+    public static double divSmoothV1(double a, double b, double zscore) {
+        // Wilson Smoothing
+        if (a == 0 || b == 0) {
+            return 0d;
+        }
+        double zscore2 = zscore * zscore;
+        double p = a / b;
+        double numerator = p + zscore2 / (2 * b) - zscore * Math.sqrt((p * (1 - p) + zscore2 / (4 * b)) / b);
+        double denominator = 1 + zscore2 / b;
+        return numerator / denominator;
+    }
 
     public static double log(double a) {
         if (a <= 0) {

ad-engine-server/src/main/resources/ad_score_config_xgboost_683.conf

@@ -2,6 +2,6 @@ scorer-config = {
   xgb-score-config = {
     scorer-name = "com.tzld.piaoquan.ad.engine.service.score.scorer.XGBoostScorer683"
     scorer-priority = 99
-    model-path = "fengzhoutian/model_xgb_351_1000_30d_v1.tar.gz"
+    model-path = "fengzhoutian/model_xgb_351_1000_30d_v2.tar.gz"
   }
 }

ad-engine-service/src/main/java/com/tzld/piaoquan/ad/engine/service/score/strategy/RankStrategyBy683.java

@@ -17,6 +17,7 @@ import org.springframework.beans.factory.annotation.Value;
 import org.springframework.stereotype.Component;
 import org.xm.Similarity;
 
+import javax.annotation.PostConstruct;
 import java.io.BufferedReader;
 import java.io.IOException;
 import java.io.InputStream;
@@ -28,6 +29,8 @@ import java.util.concurrent.Future;
 import java.util.concurrent.TimeUnit;
 import java.util.stream.Collectors;
 
+import static com.tzld.piaoquan.ad.engine.commons.math.Const.WILSON_ZSCORE;
+
 @Slf4j
 @Component
 public class RankStrategyBy683 extends RankStrategyBasic {
@@ -46,6 +49,11 @@ public class RankStrategyBy683 extends RankStrategyBasic {
     @ApolloJsonValue("${rank.score.neg_sample_rate:0.01}")
     Double negSampleRate;
 
+    @PostConstruct
+    public void afterInit() {
+        this.readBucketFile();
+    }
+
     @Override
     public List<AdRankItem> adItemRank(RankRecommendRequestParam request, ScoreParam scoreParam) {
 
@@ -183,7 +191,6 @@ public class RankStrategyBy683 extends RankStrategyBasic {
 
         long time3 = System.currentTimeMillis();
         // 分桶
-        this.readBucketFile();
         userFeatureMap = this.featureBucket(userFeatureMap);
         CountDownLatch cdl4 = new CountDownLatch(adRankItems.size());
         for (AdRankItem adRankItem : adRankItems) {
@@ -322,17 +329,19 @@ public class RankStrategyBy683 extends RankStrategyBasic {
                 double click = Double.parseDouble(feature.getOrDefault("ad_click_" + time, "0"));
                 double conver = Double.parseDouble(feature.getOrDefault("ad_conversion_" + time, "0"));
                 double income = Double.parseDouble(feature.getOrDefault("ad_income_" + time, "0"));
-                double f2 = NumUtil.div(conver, view);
-                double ecpm = NumUtil.div(income * 1000, view);
-                cidFeatureMap.put(prefix + "_" + time + "_ctr", String.valueOf(NumUtil.div(click, view)));
-                cidFeatureMap.put(prefix + "_" + time + "_ctcvr", String.valueOf(f2));
-                cidFeatureMap.put(prefix + "_" + time + "_cvr", String.valueOf(NumUtil.div(conver, click)));
+                double cpc = NumUtil.div(income, click);
+                double ctr = NumUtil.divSmoothV1(click, view, WILSON_ZSCORE);
+                double ctcvr = NumUtil.divSmoothV1(conver, view, WILSON_ZSCORE);
+                double ecpm = ctr * cpc * 1000;
+                cidFeatureMap.put(prefix + "_" + time + "_ctr", String.valueOf(ctr));
+                cidFeatureMap.put(prefix + "_" + time + "_ctcvr", String.valueOf(ctcvr));
+                cidFeatureMap.put(prefix + "_" + time + "_cvr", String.valueOf(NumUtil.divSmoothV1(conver, click, WILSON_ZSCORE)));
                 cidFeatureMap.put(prefix + "_" + time + "_conver", String.valueOf(conver));
                 cidFeatureMap.put(prefix + "_" + time + "_ecpm", String.valueOf(ecpm));
 
                 cidFeatureMap.put(prefix + "_" + time + "_click", String.valueOf(click));
                 cidFeatureMap.put(prefix + "_" + time + "_conver*log(view)", String.valueOf(conver * NumUtil.log(view)));
-                cidFeatureMap.put(prefix + "_" + time + "_conver*ctcvr", String.valueOf(conver * f2));
+                cidFeatureMap.put(prefix + "_" + time + "_conver*ctcvr", String.valueOf(conver * ctcvr));
             }
         }
 
@@ -355,17 +364,19 @@ public class RankStrategyBy683 extends RankStrategyBasic {
                 double click = Double.parseDouble(feature.getOrDefault("ad_click_" + time, "0"));
                 double conver = Double.parseDouble(feature.getOrDefault("ad_conversion_" + time, "0"));
                 double income = Double.parseDouble(feature.getOrDefault("ad_income_" + time, "0"));
-                double f2 = NumUtil.div(conver, view);
-                double ecpm = NumUtil.div(income * 1000, view);
-                cidFeatureMap.put(prefix + "_" + time + "_ctr", String.valueOf(NumUtil.div(click, view)));
-                cidFeatureMap.put(prefix + "_" + time + "_ctcvr", String.valueOf(f2));
-                cidFeatureMap.put(prefix + "_" + time + "_cvr", String.valueOf(NumUtil.div(conver, click)));
+                double cpc = NumUtil.div(income, click);
+                double ctr = NumUtil.divSmoothV1(click, view, WILSON_ZSCORE);
+                double ctcvr = NumUtil.divSmoothV1(conver, view, WILSON_ZSCORE);
+                double ecpm = ctr * cpc * 1000;
+                cidFeatureMap.put(prefix + "_" + time + "_ctr", String.valueOf(ctr));
+                cidFeatureMap.put(prefix + "_" + time + "_ctcvr", String.valueOf(ctcvr));
+                cidFeatureMap.put(prefix + "_" + time + "_cvr", String.valueOf(NumUtil.divSmoothV1(conver, click, WILSON_ZSCORE)));
                 cidFeatureMap.put(prefix + "_" + time + "_conver", String.valueOf(conver));
                 cidFeatureMap.put(prefix + "_" + time + "_ecpm", String.valueOf(ecpm));
 
                 cidFeatureMap.put(prefix + "_" + time + "_click", String.valueOf(click));
                 cidFeatureMap.put(prefix + "_" + time + "_conver*log(view)", String.valueOf(conver * NumUtil.log(view)));
-                cidFeatureMap.put(prefix + "_" + time + "_conver*ctcvr", String.valueOf(conver * f2));
+                cidFeatureMap.put(prefix + "_" + time + "_conver*ctcvr", String.valueOf(conver * ctcvr));
             }
         }
 
@@ -449,11 +460,13 @@ public class RankStrategyBy683 extends RankStrategyBasic {
             double click = Double.parseDouble(d1Feature.getOrDefault("ad_click_" + prefix, "0"));
             double conver = Double.parseDouble(d1Feature.getOrDefault("ad_conversion_" + prefix, "0"));
             double income = Double.parseDouble(d1Feature.getOrDefault("ad_income_" + prefix, "0"));
-            featureMap.put("d1_feature_" + prefix + "_ctr", String.valueOf(NumUtil.div(click, view)));
-            featureMap.put("d1_feature_" + prefix + "_ctcvr", String.valueOf(NumUtil.div(conver, view)));
-            featureMap.put("d1_feature_" + prefix + "_cvr", String.valueOf(NumUtil.div(conver, click)));
+            double cpc = NumUtil.div(income, click);
+            double ctr = NumUtil.divSmoothV1(click, view, WILSON_ZSCORE);
+            featureMap.put("d1_feature_" + prefix + "_ctr", String.valueOf(ctr));
+            featureMap.put("d1_feature_" + prefix + "_ctcvr", String.valueOf(NumUtil.divSmoothV1(conver, view, WILSON_ZSCORE)));
+            featureMap.put("d1_feature_" + prefix + "_cvr", String.valueOf(NumUtil.divSmoothV1(conver, click, WILSON_ZSCORE)));
             featureMap.put("d1_feature_" + prefix + "_conver", String.valueOf(conver));
-            featureMap.put("d1_feature_" + prefix + "_ecpm", String.valueOf(NumUtil.div(income * 1000, view)));
+            featureMap.put("d1_feature_" + prefix + "_ecpm", String.valueOf(ctr * cpc * 1000));
         }
     }
 
@@ -596,7 +609,8 @@ public class RankStrategyBy683 extends RankStrategyBasic {
             return;
         }
         synchronized (this) {
-            InputStream resourceStream = RankStrategyBy683.class.getClassLoader().getResourceAsStream("20240718_ad_bucket_688.txt");
+            String bucketFile = "20250113_ad_bucket_688.txt";
+            InputStream resourceStream = RankStrategyBy683.class.getClassLoader().getResourceAsStream(bucketFile);
             if (resourceStream != null) {
                 try (BufferedReader reader = new BufferedReader(new InputStreamReader(resourceStream))) {
                     Map<String, double[]> bucketsMap = new HashMap<>();
@@ -619,8 +633,9 @@ public class RankStrategyBy683 extends RankStrategyBasic {
                     this.bucketsMap = bucketsMap;
                     this.bucketsLen = bucketsLen;
                 } catch (IOException e) {
-                    log.error("something is wrong in parse bucket file:", e);
+                    log.error("something is wrong in parse bucket file: ", e);
                 }
+                log.info("load bucket file success: {}", bucketFile);
             } else {
                 log.error("no bucket file");
             }