LONGXIA

? · · lstm_s2

token id: #185
symbol: LONGXIA
variant: –
chain
address
cohort: datapoint (mid-window listing)
first bar: 2026-08-27
predictions: 144

Track record at +1d

assessed

47

of 48 predictions shown

direction hit

57.4%

alpha space; 50% is a coin flip

MAE (alpha)

0.2307

mean absolute log-return error

mean pred / actual

-0.0124

actual -0.0320

History

as of	split	anchor px	pred px	pred Δ	actual px	actual Δ	alpha err	hit	β90d
2026-10-22	oos	0.02106	0.02096	-0.48%	–	pending	–	–	1.35
2026-10-21	oos	0.021215	0.021117	-0.46%	0.02106	-0.73%	0.0058	✓	1.35
2026-10-20	oos	0.021195	0.021102	-0.44%	0.021215	+0.09%	0.0123	✓	1.35
2026-10-19	oos	0.020355	0.02026	-0.47%	0.021195	+4.13%	0.0273	✗	1.33
2026-10-18	oos	0.02088	0.020774	-0.51%	0.020355	-2.51%	0.0176	✓	1.33
2026-10-17	oos	0.02746	0.027375	-0.31%	0.02088	-23.96%	0.2819	✓	1.44
2026-10-16	oos	0.029085	0.028995	-0.31%	0.02746	-5.59%	0.0523	✓	1.44
2026-10-15	oos	0.029995	0.029898	-0.32%	0.029085	-3.03%	0.0167	✓	1.43
2026-10-14	oos	0.029625	0.029514	-0.37%	0.029995	+1.25%	0.0065	✗	1.43
2026-10-13	oos	0.04862	0.048231	-0.80%	0.029625	-39.07%	0.4702	✓	0.92
2026-10-12	oos	0.040295	0.040054	-0.60%	0.04862	+20.66%	0.1812	✗	0.77
2026-10-11	oos	0.04401	0.0437	-0.70%	0.040295	-8.44%	0.0656	✓	0.66
2026-10-10	oos	0.04627	0.045923	-0.75%	0.04401	-4.88%	0.0489	✓	0.69
2026-10-09	oos	0.046	0.045656	-0.75%	0.04627	+0.59%	0.0103	✗	0.69
2026-10-08	oos	0.05196	0.051464	-0.95%	0.046	-11.47%	0.1203	✓	0.77
2026-10-07	oos	0.04116	0.040804	-0.86%	0.05196	+26.24%	0.2621	✗	1.07
2026-10-06	oos	0.06616	0.065213	-1.43%	0.04116	-37.79%	0.4536	✓	0.25
2026-10-05	oos	0.04544	0.04495	-1.08%	0.06616	+45.60%	0.3874	✗	0.34
2026-10-04	oos	0.04529	0.044786	-1.11%	0.04544	+0.33%	0.0175	✗	0.34
2026-10-03	oos	0.049945	0.049398	-1.10%	0.04529	-9.32%	0.0968	✓	0.48
2026-10-02	oos	0.03919	0.038669	-1.33%	0.049945	+27.44%	0.2546	✗	0.46
2026-10-01	oos	0.110175	0.10739	-2.53%	0.03919	-64.43%	1.0077	✓	0.07
2026-09-30	oos	0.0359	0.035379	-1.45%	0.110175	+206.89%	1.1507	✗	-0.96
2026-09-29	oos	0.068975	0.068201	-1.12%	0.0359	-47.95%	0.6428	✓	-1.06
2026-09-28	oos	0.070225	0.069413	-1.16%	0.068975	-1.78%	0.0040	✓	-1.05
2026-09-27	oos	0.08775	0.0868	-1.08%	0.070225	-19.97%	0.2274	✓	-1.29
2026-09-26	oos	0.1038	0.102747	-1.01%	0.08775	-15.46%	0.1571	✓	-1.31
2026-09-25	oos	0.130175	0.128855	-1.01%	0.1038	-20.26%	0.2201	✓	1.00
2026-09-24	oos	0.10344	0.10233	-1.07%	0.130175	+25.85%	0.2441	✗	1.00
2026-09-23	oos	0.16812	0.166018	-1.25%	0.10344	-38.47%	0.4732	✓	1.00
2026-09-22	oos	0.139465	0.138058	-1.01%	0.16812	+20.55%	0.2183	✗	1.00
2026-09-21	oos	0.234285	0.229605	-2.00%	0.139465	-40.47%	0.4940	✓	1.00
2026-09-20	oos	0.238305	0.23226	-2.54%	0.234285	-1.69%	0.0561	✓	1.00
2026-09-19	oos	0.226335	0.220369	-2.64%	0.238305	+5.29%	0.0792	✗	1.00
2026-09-18	oos	0.22224	0.215912	-2.85%	0.226335	+1.84%	0.0427	✗	1.00
2026-09-17	oos	0.23069	0.223071	-3.30%	0.22224	-3.66%	0.0613	✓	1.00
2026-09-16	oos	0.21309	0.206017	-3.32%	0.23069	+8.26%	0.1104	✗	1.00
2026-09-15	oos	0.195995	0.189374	-3.38%	0.21309	+8.72%	0.1106	✗	1.00
2026-09-14	oos	0.16108	0.15612	-3.08%	0.195995	+21.68%	0.2612	✗	1.00
2026-09-13	oos	0.14472	0.140044	-3.23%	0.16108	+11.30%	0.1222	✗	1.00
2026-09-12	oos	0.154585	0.14857	-3.89%	0.14472	-6.38%	0.0202	✓	1.00
2026-09-11	oos	0.07052	0.069914	-0.86%	0.154585	+119.21%	0.7928	✗	1.00
2026-09-10	oos	0.03809	0.038224	+0.35%	0.07052	+85.14%	0.6037	✓	1.00
2026-09-09	oos	0.049155	0.049382	+0.46%	0.03809	-22.51%	0.2371	✗	1.00
2026-09-08	oos	0.05884	0.058882	+0.07%	0.049155	-16.46%	0.1785	✗	1.00
2026-09-07	oos	0.05455	0.054721	+0.31%	0.05884	+7.86%	0.0807	✓	1.00
2026-09-06	oos	0.0741	0.074034	-0.09%	0.05455	-26.38%	0.2898	✓	1.00
2026-09-05	oos	0.08774	0.087299	-0.50%	0.0741	-15.55%	0.1703	✓	1.00

predicted and realised values are beta-adjusted unless labelled otherwise: alpha = r_token − β_90d · r_BTC, so every figure means “performance versus this token’s own BTC beta”, not market direction. Prices are reconstructed under the flat-BTC assumption P̂ = P_last exp(clip(α̂, ±3)). In-sample (train) rows are excluded by default because the model trained on them. Read-only view of predictions.db.