We know that the purchase amount has been Normalized by ELO. I used the following steps to back transform the purchase amount.
\n\nStep 2 - Scaling purchase_amount back
(a) Look at differences between neighbours
\nn_merc = fread('new_merchant_transactions.csv',select = c('card_id','purchase_amount'))\n\n\nx = data.table('purchase_amount' = unique(n_merc$purchase_amount)) \n\n\ncols = 'purchase_amount'\n\n\nx[,c(\"lag1\"):=shift(.SD,1),.SDcols=cols]\n\n \nx$diff = round(x$purchase_amount - x$lag1,8)\n\n\nc = x %>% group_by(diff) %>% summarise(cnt = n()) %>% arrange(desc(cnt))\n\n\nx$transformed = (x$purchase_amount / 0.00001503)\n\n\nx$transformed = x$transformed - min(x$transformed)\n\n\nx$transformed = log1p(x$transformed)\n
Applying log1p over the transformed purchase amount gave 0.04 boost along with aggregate features derived from it.
\n\nCLV - This is my kernel explaining the basics of it. Lifetime package in python automatically calculates R (Recency), F (Frequency) , T (Time) and M (Monitary value). (Lifetimes) This also helps us calculate predicted purchases using regression techniques (you will have to specify time frame in days as prediction period for purchase amount) In addition, two way interactions between R,F,M and T were also included. (+,-,*,)
\n\nOleg's regression features. Transformed the purchase amount as mentioned above, before running regression.
\n\nAggregate features from hist_transactions, splitting based on authorized and unauthorized transactions before aggregation was very useful. Similar aggregates for new_transactions table.
\n\nShout out to Olivier for sharing this remarkable kernel on feature selection using NULL IMPORTANCE. Several thresholds for feature importance was used iteratively to remove insignificant features.
\n\nRegression Model trained without outliers\n1. LightGBM \n2. XgBoost
\n\nClassification Model\n1. LightGBM model for binary classification.\n2. Optimal threshold for classifying probabilities into class 1 (outlier) and 0 (not outlier) was determined using KStat\n3. Built a Ridge regression over 2207 outliers with some additional rows (having low loyalty scores) and predicted over the results which has class 1 from step 2.
\n\nCombined both regression and classification model results. Best private score was 3.611 which would have helped our team end at silver position instead of a bronze. None the less, it was an amazing contest.
\n\nWe know that the purchase amount has been Normalized by ELO. I used the following steps to back transform the purchase amount.
\n\nStep 2 - Scaling purchase_amount back
(a) Look at differences between neighbours
\nn_merc = fread('new_merchant_transactions.csv',select = c('card_id','purchase_amount'))\n\n\nx = data.table('purchase_amount' = unique(n_merc$purchase_amount)) \n\n\ncols = 'purchase_amount'\n\n\nx[,c(\"lag1\"):=shift(.SD,1),.SDcols=cols]\n\n \nx$diff = round(x$purchase_amount - x$lag1,8)\n\n\nc = x %>% group_by(diff) %>% summarise(cnt = n()) %>% arrange(desc(cnt))\n\n\nx$transformed = (x$purchase_amount / 0.00001503)\n\n\nx$transformed = x$transformed - min(x$transformed)\n\n\nx$transformed = log1p(x$transformed)\n
Applying log1p over the transformed purchase amount gave 0.04 boost along with aggregate features derived from it.
\n\nCLV - This is my kernel explaining the basics of it. Lifetime package in python automatically calculates R (Recency), F (Frequency) , T (Time) and M (Monitary value). (Lifetimes) This also helps us calculate predicted purchases using regression techniques (you will have to specify time frame in days as prediction period for purchase amount) In addition, two way interactions between R,F,M and T were also included. (+,-,*,)
\n\nOleg's regression features. Transformed the purchase amount as mentioned above, before running regression.
\n\nAggregate features from hist_transactions, splitting based on authorized and unauthorized transactions before aggregation was very useful. Similar aggregates for new_transactions table.
\n\nShout out to Olivier for sharing this remarkable kernel on feature selection using NULL IMPORTANCE. Several thresholds for feature importance was used iteratively to remove insignificant features.
\n\nRegression Model trained without outliers\n1. LightGBM \n2. XgBoost
\n\nClassification Model\n1. LightGBM model for binary classification.\n2. Optimal threshold for classifying probabilities into class 1 (outlier) and 0 (not outlier) was determined using KStat\n3. Built a Ridge regression over 2207 outliers with some additional rows (having low loyalty scores) and predicted over the results which has class 1 from step 2.
\n\nCombined both regression and classification model results. Best private score was 3.611 which would have helped our team end at silver position instead of a bronze. None the less, it was an amazing contest.
\n\n