Assignment 7

Modified: 2015/01/14 02:43 by admin - Uncategorized

We create a Google Group for the discussions. If you have any question, please post it there so everybody can see our reply, and try not to send us your questions directly via emails.

Edit

The Task: Participating in the Kaggle Competition

Now, You Are Ready

In this assignment, you are asked to participate in an ongoing real-world data mining competition held by kaggle (a place where you can compete with world-class data miners on real data mining applications and at the same time possibly earn a handsome prize). This year, you are asked to design and implement data mining methods to solve the following problem:

Click-Through Rate Prediction, $15,000 (prize)

You can click the title above to get all the information you need to accomplish the competition, including how to register, how to get the data, how to evaluate your method. Nonetheless, we give a brief guidance for the newcomers of kaggle:

You can sign up a new account or use an existing Google account to sign in kaggle here
Find the competition homepage here, where you should read the description, evaluation, rules, prize and all the information you need to know.
Accept the licence before downloading the training and test data here.
Then use any methods you have learned to build a model from training examples, and then use this model to predict the test samples, and submit the prediction file here to evaluate your result and get your rank almost instantaneously which will be shown in a leaderboard.
Modify the Team Name (the name shown in the leaderboard, not your account name) in My Team as your student number, such as

Your Task:

Participate in this competition and get higher rank as you can.
You are encouraged to use the codes you have already written in previous assignments. (5% rewards)
Write a report to describe your methods and implementation.
Submit your code, as well as the prediction file.

Edit

Data

We have downloaded these data for you, which you can find at ftp://lamda.nju.edu.cn/mg_dm14/Data/

Edit

Submission

Please use this MSWord template to report your results.
Do NOT plagiarize, plagiarism will be seriously penalized: You should be careful on writing your report. Whenever you are using words and works of others, citations should be made clear such that one can tell which part is actually yours. Details about how to identify a plagiarism can be found in "Introduction to the Guidelines for Handling Plagiarism Complaints".
Do NOT falsify results, data fraud will be even more seriously penalized: You should honestly record your results in the report, NEVER EVER modify the performance results manually.
Pack your report , code and Submission.csv into a zip file named with your student ID, e.g., 'MG1433001.zip'. If you have multiple submissions, add an extra '_' with a number, such as 'MG1433001_1.zip'. We will use the the version with the largest number as your final submission.
- The file format should be zip, no other format is acceptable!
- NO submission after the deadline is acceptable!
- NO email submission will be accepted!

Upload your file to FTP: (please use FTP software to upload, do not use Windows Explorer or IE)
ftp://lamda.nju.edu.cn/mg_dm14/assignment7/
username/password: You will be informed in the first class

Edit

Evaluation

We will evaluate your submission according to your rank and report.

For rank:
We will get your absolute rank (the rank over all the participants, p₁) and relative rank (the rank over all the students from this course, p₂) from the leaderboard, say, r₁ and r₂, then your final score for the rank part is given by:

where I is an indicator function and I(condition)=1 if condition is true, 0 otherwise.

For report:
Technique: clearly explain why you choose such method, how you implement the method, and how the method perform on this data mining task
Language: concise, precise, and logical.
Organization: good structure, clearly and properly separated sections and paragraphs.
Citations: all works of non-yourself should have correct references.

If plagiarism is identified, no scores will be given to this report.

Edit

Leaderboard (final version)

Absolute Rank	Relative Rank	Name	Score	Entries	Best Submission UTC
29	1	MG1433064	0.3901400	39	Fri, 09 Jan 2015 12:18:40
30	2	MG1433011	0.3901897	54	Tue, 13 Jan 2015 09:32:04
37	3	MF1433016	0.3905062	32	Sat, 10 Jan 2015 12:11:53
43	4	DZ1433035	0.3907622	19	Tue, 13 Jan 2015 04:52:53
46	5	MG1433046	0.3908217	26	Sat, 10 Jan 2015 14:56:22
52	6	MG1433065	0.3909129	44	Sat, 10 Jan 2015 15:04:45
53	7	MG1433073	0.3909293	13	Sat, 10 Jan 2015 12:27:24
54	8	MG1433067	0.3909616	16	Sun, 11 Jan 2015 15:22:06
56	9	MG1433075	0.3910175	85	Sun, 11 Jan 2015 07:20:49
59	11	MF1433028	0.3910622	9	Sat, 10 Jan 2015 11:04:55
63	12	DZ1433012	0.3911588	18	Sat, 10 Jan 2015 15:03:55
64	13	MG1433019	0.3911694	26	Mon, 12 Jan 2015 01:45:12
65	14	MG1433027	0.3911806	22	Sun, 11 Jan 2015 07:14:15
71	15	MG1433016	0.3913378	5	Sat, 10 Jan 2015 14:58:45
72	16	MG1433051	0.3913611	123	Fri, 09 Jan 2015 08:37:42
74	17	DZ1433026	0.3913693	14	Mon, 12 Jan 2015 13:06:54
84	18	MG1433077	0.3915606	36	Wed, 07 Jan 2015 15:11:25
96	19	MG1433036	0.3917560	10	Sat, 10 Jan 2015 14:04:24
120	20	MG1433029	0.3922727	7	Sun, 11 Jan 2015 02:55:29
122	21	DZ1433037	0.3922970	61	Sat, 10 Jan 2015 11:32:21
151	22	DZ1433020	0.3928960	1	Fri, 09 Jan 2015 15:21:55
155	23	MG1433050	0.3930294	31	Wed, 07 Jan 2015 04:40:09
163	24	MG1433035	0.3931626	4	Wed, 07 Jan 2015 03:03:57
190	25	MG1433033	0.3934774	33	Sat, 10 Jan 2015 06:27:37
192	26	MG1433081	0.3934818	17	Fri, 09 Jan 2015 10:57:51
196	27	MG1433066	0.3935003	29	Sat, 10 Jan 2015 01:05:22
197	28	MG1433039	0.3935025	35	Sun, 11 Jan 2015 12:10:09
198	29	MF1433033	0.3935049	4	Sat, 10 Jan 2015 15:11:26
203	30	MF1433060	0.3935336	20	Sat, 10 Jan 2015 07:52:18
204	31	MG1433021	0.3935455	9	Sat, 10 Jan 2015 01:27:27
205	32	MF1433024	0.3935483	45	Sun, 11 Jan 2015 04:28:12
206	33	MG1433091	0.3935487	26	Thu, 18 Dec 2014 15:08:41
208	34	MF1433020	0.3935522	11	Sat, 10 Jan 2015 09:19:29
209	35	MG1433049	0.3935540	2	Fri, 09 Jan 2015 05:26:30
210	36	MG1433096	0.3935540	5	Sat, 10 Jan 2015 12:25:17
211	37	MG1433086	0.3935540	3	Sat, 10 Jan 2015 05:42:12
212	38	MF1433027	0.3935553	20	Sat, 10 Jan 2015 05:20:26
213	39	MG1433040	0.3935669	9	Fri, 09 Jan 2015 13:40:00
214	40	MF1433041	0.3935669	17	Sat, 10 Jan 2015 15:00:31
215	41	MF1433031	0.3935690	17	Sat, 03 Jan 2015 07:10:26
217	42	MG1433028	0.3935720	54	Tue, 13 Jan 2015 12:32:55
219	43	MF1433035	0.3935767	26	Sat, 10 Jan 2015 13:32:41
220	44	MF1433034	0.3935768	4	Sat, 10 Jan 2015 14:32:37
221	45	MF1433012	0.3935795	29	Sun, 11 Jan 2015 10:46:07
222	46	MG1433059	0.3935941	26	Fri, 09 Jan 2015 15:27:39
226	47	MF1433002	0.3936047	16	Sat, 10 Jan 2015 15:42:00
228	48	MF1433045	0.3936186	7	Tue, 23 Dec 2014 08:47:28
229	49	MG1433047	0.3936206	23	Mon, 12 Jan 2015 08:35:42
232	50	MF1433022	0.3936238	27	Sat, 10 Jan 2015 14:15:02
233	51	B111220022	0.3936238	9	Sat, 10 Jan 2015 14:53:35
241	52	MF1433011	0.3936419	13	Tue, 30 Dec 2014 13:06:10
244	53	DZ1433047	0.3936488	10	Wed, 07 Jan 2015 06:39:30
246	54	MF1433017	0.3936497	3	Sat, 10 Jan 2015 12:08:59
247	55	MG1433003	0.3936539	3	Sat, 10 Jan 2015 10:49:25
250	56	MG1433037	0.3936575	19	Sat, 10 Jan 2015 06:24:13
256	57	DZ1433018	0.3936795	33	Sat, 10 Jan 2015 06:13:08
257	58	MF1433048	0.3936823	4	Sat, 10 Jan 2015 06:25:57
258	59	MF1433030	0.3936856	29	Sat, 10 Jan 2015 09:29:39
259	60	MF1433051	0.3936893	48	Fri, 09 Jan 2015 13:34:12
263	61	MG1433045	0.3937075	61	Sat, 10 Jan 2015 08:15:38
268	62	MG1433088	0.3937178	7	Sat, 10 Jan 2015 14:49:04
273	63	MF1433010	0.3937368	37	Tue, 06 Jan 2015 11:18:35
278	64	MF1433042	0.3937545	1	Wed, 31 Dec 2014 12:51:25
279	65	DZ1433036	0.3937676	1	Sat, 10 Jan 2015 05:29:32
282	66	MF1433047	0.3937894	11	Fri, 09 Jan 2015 08:18:09
283	67	MG1433014	0.3937940	21	Sat, 10 Jan 2015 05:14:30
290	68	MG1433070	0.3938061	2	Sat, 10 Jan 2015 08:44:13
291	69	MG1433090	0.3938061	2	Sat, 10 Jan 2015 13:59:20
292	70	MF1433059	0.3938061	2	Sat, 10 Jan 2015 15:04:15
293	71	MF1433040	0.3938061	2	Sat, 10 Jan 2015 17:56:07
294	72	MG1433007	0.3938063	1	Sat, 10 Jan 2015 11:25:23
295	73	MF1433065	0.3938106	12	Sun, 11 Jan 2015 08:45:03
297	74	MF1433055	0.3938189	2	Sat, 10 Jan 2015 11:55:00
298	75	MF1433054	0.3938194	4	Sat, 10 Jan 2015 12:37:08
301	76	MG1433032	0.3938230	15	Tue, 13 Jan 2015 02:50:27
302	77	MG1433048	0.3938346	6	Tue, 13 Jan 2015 07:58:11
307	78	B111220016	0.3938571	6	Sat, 10 Jan 2015 09:59:45
308	79	MG1433083	0.3938586	41	Sat, 10 Jan 2015 10:54:01
309	80	MG1433072	0.3938616	1	Sat, 10 Jan 2015 10:14:30
317	81	MG1433042	0.3938713	43	Sat, 10 Jan 2015 09:52:46
321	82	MF1433013	0.3939045	4	Sat, 10 Jan 2015 11:05:57
326	83	MF1433058	0.3939272	5	Sat, 10 Jan 2015 15:16:26
329	84	MG1433054	0.3939481	5	Sat, 10 Jan 2015 15:14:21
331	85	MF1433025	0.3939555	5	Sat, 10 Jan 2015 14:03:02
333	86	MG1433043	0.3939589	30	Sat, 10 Jan 2015 05:36:37
342	87	MF1433049	0.3939938	9	Mon, 05 Jan 2015 12:35:23
344	88	MG1433017	0.3940218	13	Sat, 10 Jan 2015 11:06:45
352	89	MF1433052	0.3940388	7	Sat, 10 Jan 2015 08:27:06
354	90	MG1433074	0.3940719	8	Sat, 10 Jan 2015 06:52:13
356	91	MG1426010	0.3940756	41	Tue, 23 Dec 2014 08:03:50
357	92	MG1433080	0.3940867	17	Sat, 10 Jan 2015 12:50:53
359	93	MF1433021	0.3940902	11	Sat, 10 Jan 2015 14:26:53
363	94	MF1433015	0.3940986	4	Sat, 10 Jan 2015 14:23:46
364	95	DZ1433030	0.3941052	23	Sun, 11 Jan 2015 12:42:53
365	96	DZ1433027	0.3941100	2	Sun, 14 Dec 2014 06:58:58
376	97	MG1433057	0.3941480	6	Sat, 10 Jan 2015 08:52:10
377	98	MG1433053	0.3941558	21	Sat, 10 Jan 2015 04:44:16
381	99	MF1433004	0.3941819	5	Sat, 10 Jan 2015 06:59:20
385	100	B111220162	0.3942141	20	Wed, 07 Jan 2015 10:48:39
390	101	MG1433097	0.3943484	4	Sat, 10 Jan 2015 12:59:21
393	102	MF1433050	0.3943810	23	Sat, 10 Jan 2015 20:07:34
397	103	MG1433062	0.3943915	32	Sat, 10 Jan 2015 01:41:26
405	104	B111220018	0.3944280	12	Sat, 10 Jan 2015 13:57:57
408	105	MF1433067	0.3944777	5	Sat, 10 Jan 2015 14:15:37
412	106	MG1433087	0.3945042	40	Thu, 25 Dec 2014 05:54:20
419	107	MF1433014	0.3945660	18	Sat, 10 Jan 2015 09:12:34
438	108	MG1433054	0.3946811	5	Sat, 10 Jan 2015 14:45:53
439	109	MG1433078	0.3946826	16	Mon, 12 Jan 2015 05:58:01
441	110	MG1433085	0.3946826	4	Sat, 10 Jan 2015 08:26:16
442	111	MG1333021	0.3946850	1	Sat, 10 Jan 2015 08:29:32
444	112	DZ1433017	0.3946913	9	Sat, 10 Jan 2015 05:42:07
453	113	MF1433064	0.3947231	2	Sat, 10 Jan 2015 10:53:22
461	114	MG1433095	0.3947523	9	Sat, 10 Jan 2015 03:21:37
463	115	MG1433006	0.3947568	5	Sat, 10 Jan 2015 13:11:11
464	116	MF1433039	0.3947585	11	Tue, 13 Jan 2015 10:35:23
471	117	MF1433066	0.3947854	6	Sat, 03 Jan 2015 03:05:25
477	118	MG1433079	0.3948038	8	Mon, 05 Jan 2015 03:08:54
483	119	MF1433026	0.3948501	5	Sat, 10 Jan 2015 15:51:52
485	120	DZ1433006	0.3948531	6	Sat, 10 Jan 2015 13:46:49
489	121	MF1433023	0.3948761	2	Sat, 10 Jan 2015 13:22:35
490	122	MF1433003	0.3948784	2	Sat, 03 Jan 2015 10:09:44
491	123	MF1433043	0.3948784	2	Sat, 10 Jan 2015 15:26:20
492	124	MF1433019	0.3948795	1	Sat, 03 Jan 2015 10:33:14
493	125	MF1433038	0.3948795	3	Sat, 10 Jan 2015 16:07:25
496	126	MF1433046	0.3948923	15	Sat, 10 Jan 2015 10:24:16
501	127	MG1433055	0.3949001	5	Sat, 10 Jan 2015 15:33:20
503	128	MG1433044	0.3949036	5	Sat, 10 Jan 2015 15:00:24
506	129	B111220103	0.3949040	16	Sat, 10 Jan 2015 11:58:03
509	130	MG1433015	0.3949186	14	Sat, 10 Jan 2015 01:59:08
513	131	MG1333097	0.3949413	1	Mon, 29 Dec 2014 12:18:58
515	132	MG1433076	0.3949444	1	Sat, 10 Jan 2015 10:58:44
516	133	MG1433009	0.3949463	14	Wed, 07 Jan 2015 05:56:53
517	134	MG1433030	0.3949468	5	Sat, 10 Jan 2015 08:54:23
519	135	MG1433082	0.3949654	16	Sat, 10 Jan 2015 05:50:03
520	136	MG1433068	0.3949664	19	Fri, 09 Jan 2015 11:44:56
525	137	DZ1433038	0.3949751	3	Sat, 10 Jan 2015 07:03:07
526	138	MG1433012	0.3949884	4	Sat, 10 Jan 2015 12:46:48
534	139	MG1433041	0.3950456	5	Sun, 21 Dec 2014 09:21:42
537	140	MG1433013	0.3950733	9	Sat, 10 Jan 2015 08:11:00
538	141	MG1433022	0.3950751	4	Sat, 10 Jan 2015 15:35:15
539	142	DZ1433013	0.3950820	1	Fri, 09 Jan 2015 17:24:48
540	143	MG1433002	0.3950835	12	Sat, 20 Dec 2014 04:11:16
542	144	MF1433029	0.3950852	3	Tue, 06 Jan 2015 14:59:49
546	145	MG1433020	0.3951129	3	Sat, 10 Jan 2015 05:53:06
564	146	MG1433071	0.3952684	40	Sat, 10 Jan 2015 11:42:54
568	147	MF1433062	0.3952892	1	Thu, 08 Jan 2015 17:10:28
583	148	MF1433032	0.3953505	4	Sat, 10 Jan 2015 14:46:32
585	149	MG1433060	0.3953735	2	Fri, 02 Jan 2015 07:49:17
587	150	MF1433044	0.3953735	1	Sat, 10 Jan 2015 13:10:51
588	151	MG1433058	0.3953735	12	Sat, 10 Jan 2015 11:08:35
589	152	MF1433005	0.3953735	1	Sat, 10 Jan 2015 12:41:55
590	153	MF1433007	0.3953813	21	Sat, 10 Jan 2015 07:42:52
594	154	MF1433061	0.3953924	3	Fri, 09 Jan 2015 09:46:16
606	155	MG1433052	0.3954144	5	Sat, 10 Jan 2015 13:18:12
608	156	MG1433004	0.3954144	1	Sat, 10 Jan 2015 10:36:38
612	157	MF1433036	0.3954383	17	Sat, 10 Jan 2015 12:26:43
615	158	MF1433006	0.3954688	7	Tue, 06 Jan 2015 00:21:46
630	159	MG1433008	0.3955861	3	Mon, 12 Jan 2015 13:10:08
650	160	JLSS201426	0.3956372	1	Sat, 10 Jan 2015 07:14:51
657	161	MF1433057	0.3957046	8	Fri, 09 Jan 2015 02:07:27
658	162	MG1433099	0.3957063	2	Tue, 30 Dec 2014 13:31:38
667	163	MG1433094	0.3958447	6	Sat, 10 Jan 2015 13:11:44
668	164	MG1433084	0.3958460	2	Sat, 10 Jan 2015 12:26:37
671	165	DG1333032	0.3958760	35	Sat, 10 Jan 2015 08:41:12
683	166	MG1433001	0.3961851	8	Sat, 20 Dec 2014 09:29:40
693	167	MG1433018	0.3963281	10	Sat, 10 Jan 2015 13:10:46
716	168	MG1433031	0.3967375	3	Sat, 10 Jan 2015 12:08:05
797	169	MG1433063	0.3975021	20	Sat, 10 Jan 2015 13:05:29
808	170	MG1433093	0.3976180	32	Sat, 10 Jan 2015 13:52:05
835	171	MG1433089	0.3976856	3	Sun, 11 Jan 2015 08:57:26
861	172	MG1433061	0.3978622	8	Sat, 10 Jan 2015 14:21:40
867	173	MF1433001	0.3979919	2	Sat, 10 Jan 2015 13:32:36
924	174	MG1433098	0.3989911	2	Sat, 10 Jan 2015 12:07:02
961	175	MF1433009	0.4007010	4	Sat, 10 Jan 2015 14:33:13
1045	176	MG1433005	0.4101090	4	Fri, 26 Dec 2014 06:24:36
1053	177	MG1433038	0.4116334	1	Sat, 10 Jan 2015 11:45:19
1195	178	MF1433037	0.4390581	1	Sat, 03 Jan 2015 05:37:35
1300	179	MG1433025	0.5661886	10	Sat, 10 Jan 2015 07:42:42
1302	180	MG1433024	0.6295164	5	Sat, 10 Jan 2015 10:43:48
1381	181	MG1433026	0.6931472	4	Sat, 10 Jan 2015 11:17:33
1392	182	MG1433056	0.8780831	7	Sat, 10 Jan 2015 11:22:13
1416	183	MG1433069	5.5707424	1	Sat, 10 Jan 2015 10:25:46
1423	184	MF1433053	8.4378363	1	Sat, 10 Jan 2015 13:29:33

Edit

Contact TA

Mr. Qing Da and Mr. Yue Zhu

Back to assignment homepage
Back to course homepage