Update README.md
Browse files
README.md
CHANGED
@@ -64,29 +64,31 @@ FinanceBERT was evaluated on a held-out test set and achieved the following perf
|
|
64 |
|
65 |
Classification Report:
|
66 |
|
67 |
-
class_index: 0
|
68 |
- precision: 0.84
|
69 |
- recall: 0.90
|
70 |
- f1_score: 0.87
|
71 |
- support: 29
|
72 |
|
73 |
-
class_index: 1
|
74 |
- precision: 0.94
|
75 |
- recall: 0.94
|
76 |
- f1_score: 0.94
|
77 |
- support: 199
|
78 |
|
79 |
-
class_index: 2
|
80 |
- precision: 0.90
|
81 |
- recall: 0.88
|
82 |
- f1_score: 0.89
|
83 |
- support: 83
|
84 |
|
85 |
Confusion Matrix:
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
|
|
|
|
90 |
|
91 |
# Limitations
|
92 |
FinanceBERT has been rigorously trained and tested to ensure reliable performance across a variety of financial texts. However, there are several limitations to consider:
|
|
|
64 |
|
65 |
Classification Report:
|
66 |
|
67 |
+
Negative Sentiment - class_index: 0
|
68 |
- precision: 0.84
|
69 |
- recall: 0.90
|
70 |
- f1_score: 0.87
|
71 |
- support: 29
|
72 |
|
73 |
+
Neutral Sentiment - class_index: 1
|
74 |
- precision: 0.94
|
75 |
- recall: 0.94
|
76 |
- f1_score: 0.94
|
77 |
- support: 199
|
78 |
|
79 |
+
Positive Setniment - class_index: 2
|
80 |
- precision: 0.90
|
81 |
- recall: 0.88
|
82 |
- f1_score: 0.89
|
83 |
- support: 83
|
84 |
|
85 |
Confusion Matrix:
|
86 |
+
|
87 |
+
| Predicted | Negative | Neutral | Positive |
|
88 |
+
|-----------------|----------|---------|----------|
|
89 |
+
| Actual Negative | 26 | 2 | 1 |
|
90 |
+
| Actual Neutral | 4 | 188 | 7 |
|
91 |
+
| Actual Positive | 1 | 9 | 73 |
|
92 |
|
93 |
# Limitations
|
94 |
FinanceBERT has been rigorously trained and tested to ensure reliable performance across a variety of financial texts. However, there are several limitations to consider:
|