<h3>&nbsp;</h3>

<p><img alt="" src="https://storage.yandexcloud.net/datasouls-ods/images/2020/04/17/a3335983-fa79-408e-a3fc-6e302bf22673/3-3.png" /></p>

<h2>Description</h2>

<p>X5 uses text messages to encourage customers to shop more. Sending texts is costly, so we would like to target a specific group of clients, typically those who would see this as a compelling event. In other words, the goal is to target those customers who wouldn&rsquo;t have made a purchase without this communication. The goal is to develop an algorithm that predicts whether or not we should send a text message to the client.</p>

<p>This is called uplift modeling problem, see <a href="https://youtu.be/yFQAIJBYXI0">this video</a> for more details (video is in Russian, you can use auto subtitles).</p>

<h2>Quality criteria</h2>

<p>In uplift modeling tasks, clients from the test sample are ranked using descending predicted communication efficiency. The top 30% are selected from such a ranked list as the &ldquo;most promising&rdquo; sub-sample. This sub-sample is used to estimate the average added conversion. In a sense, we calculate the average increase in response to the impact on a client.</p>

<h2>Prizes</h2>

<p>Prize fund is 400&rsquo;000 RUR. The winning team will receive 150&rsquo;000 RUR; second place gets 100&rsquo;000 RUR; third place receives 50&rsquo;000 RUR; fourth and fifth places both get 25&rsquo;000 RUR. There is also a nomination for the best open-sourced solution with a prize of 50&rsquo;000 RUR. Teams of up to 4 people from all over the world are allowed, regardless of actual physical location. You are entitled to participate in different teams in multiple Retail Hero contests.</p>

Predict how much the purchase probability could increase as a result of sending an advertising SMS

Private

https://storage.yandexcloud.net/ds-ods/files/media/meta_tag/file/f6b873f39c14/banner.jpg

description

X5 Retail Hero: Uplift Modeling for Promotional Campaign

Predictions

dmitry

kirillix

alwayswannadie

FESE

ga239

paulnumberone

artiomvazh99

nekotleta

empty & yalogachev

stason

paxmet92

uberkinder

nugres

drts

bigdatasmb

toohardforme

egorborisov

maks-sh

ilya.larchenko

ArkadiyV

tolkachnik

prodigy

schigin

legchikov

kislinskiy.vg

ekaterinae

slivka_83

bitlater

vs111

mayermax

kate

metaknight

lavrik

chufistovvn

feodosiikotov and zaikoval

хоп-хэй-ла-ла-лэй

jingobox

tovvelie

no_name

AnatolyOsipov

irymsho

Make me apologize if you can

voronoffart

elena-shirokova

dvr.energy

Score

#	Teams (269)	Score	Last	Entries
1	dmitry	0.113327855	3y	133
2	kirillix	0.0989845969	3y	18
3	alwayswannadie	0.0983358676	3y	14
4	FESE	0.0983302841	3y	35
5	ga239	0.0969380695	3y	16
6	AS	0.0964346995	3y	69
7	paulnumberone	0.0958712491	3y	202
8	artiomvazh99	0.0956328467	3y	192
9	nekotleta	0.095437797	3y	48
10	empty & yalogachev	0.0951309264	3y	132
11	8	0.0949180471	3y	39
12	stason	0.0946631571	3y	105
13	paxmet92	0.0944507796	3y	32
14	uberkinder	0.0941984182	3y	76
15	nugres	0.0940875685	3y	2
16	drts	0.0938767499	3y	22
17	bigdatasmb	0.0936871038	3y	15
18	toohardforme	0.0936476817	3y	18
19	egorborisov	0.0932127675	3y	23
20	maks-sh	0.0931682404	3y	11
21	ilya.larchenko	0.0928321454	3y	41
22	ArkadiyV	0.0927319842	3y	7
23	eam	0.0927148256	3y	20
24	M&A	0.0926143166	3y	41
25	tolkachnik	0.0925591134	3y	16
26	prodigy	0.0922532863	3y	72
27	khd	0.0921365175	3y	43
28	schigin	0.0921268832	3y	46
29	legchikov	0.0920250691	3y	30
30	kislinskiy.vg	0.0920224204	3y	7
31	ekaterinae	0.0919490167	3y	79
32	slivka_83	0.0919261899	3y	161
33	bitlater	0.0918558288	3y	32
34	vs111	0.0917676382	3y	46
35	mayermax	0.0916741394	3y	15
36	kate	0.0916485808	3y	60
37	metaknight	0.091634825	3y	29
38	lavrik	0.091547113	3y	26
39	chufistovvn	0.0914168285	3y	18
40	feodosiikotov and zaikoval	0.0913490561	3y	9
41	хоп-хэй-ла-ла-лэй	0.0912765742	3y	8
42	jingobox	0.0912693608	3y	15
43	tovvelie	0.091233797	3y	43
44	no_name	0.0909174969	3y	18
45	AnatolyOsipov	0.0907274675	3y	12
46	irymsho	0.0906507549	3y	9
47	Make me apologize if you can	0.0906428597	3y	56
48	voronoffart	0.0905552677	3y	13
49	elena-shirokova	0.0905541411	3y	3
50	dvr.energy	0.0904590249	3y	14