After decompressing the file, you would get "s1.csv" file. This file contains data for one particular stock only and has the following header: date,b0,a0,bsz0,bidx0,sidx0,ssz0,bsz1,bidx1,sidx1,ssz1,bsz2,bidx2,sidx2,ssz2,bsz3,bidx3,sidx3,ssz3,bsz4,bidx4,sidx4,ssz4,f25,f26,f27,f28,f29,f30,f31,f32,f33,f34,f35,f36,f37,f38,f39,f40,f41,f42,f43,f44,f45,f46,f47,f48,f49,f50,f51,f52,f53,f54,f55,f56,f57,f58,b0_cm,a0_cm,bsz0_cm,bidx0_cm,sidx0_cm,ssz0_cm,bsz1_cm,bidx1_cm,sidx1_cm,ssz1_cm,bsz2_cm,bidx2_cm,sidx2_cm,ssz2_cm,bsz3_cm,bidx3_cm,sidx3_cm,ssz3_cm,bsz4_cm,bidx4_cm,sidx4_cm,ssz4_cm,f82,f83,f84,f85,f86,f87,f88,f89,f90,f91,f92,f93,f94,f95,f96,f97,f98,f99,f100,f101,f102,f103,f104,f105,f106,f107,f108,f109,f110,f111,f112,f113,f114,f115,f116,f117,f118,f119,f120,f121,f122,f123,f124,f125,f126,f127,f128,f129,f130,f131,f132,f133,f134,f139,f140,f141,f142,f143,f144,f145,f146,f147,f148,30secAhead,1minAhead There are 144 fields separated by comma in the file. Description of the field names are as follows : date refers to particular time of at which the data is captured. b0/b0_cm and a0/a0_cm refers to top bid and top ask for future and cash segment for the respective stock. bidx[0-4] and sidx[0-4] refers to distance from top level for bid/ask bsz[0-4] and ssz[0-4] refers to size at that level. There are different features pre-computed ( e.g.. momentum ) which are also given. ( e.g.. f1,f2, ... f148 ) 30secAhead and 1minAhead are prices 30 seconds and 1 minutes in future. These columns should not be used for prediction/classification purpose. Expectation : The idea is to create trading strategy using this data. With that in mind, you need to analyze the data set and come up with whatever interesting insights you may within a week which may lead to creation of buy/sell strategy.